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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

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

    URLs followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.92
     Chwiliwch
    -0.90
    GEBURTSDATUM
    -0.89
    parsedMessage
    -0.88
     mergeFrom
    -0.88
     AssemblyVersion
    -0.85
    webElementXpaths
    -0.84
     CreateTagHelper
    -0.83
    ResumeLayout
    -0.83
    دانشنامهٔ
    -0.81
    POSITIVE LOGITS
    8
    0.61
    5
    0.59
    0
    0.58
    7
    0.58
    6
    0.57
    9
    0.57
    3
    0.56
    4
    0.55
    Sparse
    0.51
     gunner
    0.49
    Act Density 0.270%

    No Known Activations