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

    Neuronpedia

    INDEX
    Explanations

    variables and measurements related to configurations and specifications

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

    life imprisonment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.71
    __*/
    -0.55
    RefNanny
    -0.52
    LabelTagHelper
    -0.51
     дописавши
    -0.51
    Personendaten
    -0.50
    IsMutable
    -0.49
    RTSN
    -0.49
    RegressionTest
    -0.49
    itoneum
    -0.49
    POSITIVE LOGITS
     AssemblyCompany
    0.41
    balleur
    0.36
     ark
    0.36
    gemeester
    0.34
    Seasons
    0.34
    ゆき
    0.34
    colage
    0.32
     highs
    0.32
    🖨
    0.31
    ゴリー
    0.31
    Act Density 0.010%

    No Known Activations