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

    Neuronpedia

    INDEX
    Explanations

    Alternation or changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condem
    -0.07
    stan
    -0.06
     Man
    -0.06
     timestamps
    -0.06
    _encrypt
    -0.06
    THING
    -0.06
    EMA
    -0.06
     sewing
    -0.06
    _pow
    -0.06
     formerly
    -0.06
    POSITIVE LOGITS
     conseils
    0.06
    RESP
    0.06
    :NS
    0.06
    alement
    0.06
    responseData
    0.06
    ’en
    0.06
     Cabr
    0.06
    .UIManager
    0.06
     UIB
    0.06
    .ADMIN
    0.06
    Act Density 0.025%

    No Known Activations