Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variables and mathematical symbols in numerical equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Solving equations, isolating a variable

    np_acts-logits-general · gemini-2.0-flash

    solving for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    routeProvider
    -0.42
    úmenes
    -0.42
    WriteTagHelper
    -0.41
    ⤹
    -0.41
     gancho
    -0.41
    openConnection
    -0.39
    aktery
    -0.37
     davran
    -0.35
     ujednoznacz
    -0.35
    Filmografia
    -0.35
    POSITIVE LOGITS
     <=",
    0.64
     ब्रेकडाउन
    0.56
    最快更新
    0.56
    abestanden
    0.48
    참고
    0.46
    awtextra
    0.46
    PreferredItem
    0.45
    -------------</
    0.44
    хьтан
    0.44
     >=",
    0.43
    Act Density 0.872%

    No Known Activations