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

    Neuronpedia

    INDEX
    Explanations

    instances of something working or not working, and the degree to which it does

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.80
    OGND
    -0.77
    ReusableCell
    -0.77
     صوتيه
    -0.75
    WriteTagHelper
    -0.73
     Signalez
    -0.70
     ſtate
    -0.70
     dAtA
    -0.68
     fubject
    -0.68
     Wikimedijinoj
    -0.67
    POSITIVE LOGITS
    SuspendLayout
    0.45
     مشين
    0.42
     đâu
    0.42
     for
    0.40
    wpdb
    0.39
     combineReducers
    0.39
     since
    0.39
    tvguidetime
    0.38
     ok
    0.38
     at
    0.36
    Act Density 0.858%

    No Known Activations