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

    Neuronpedia

    INDEX
    Explanations

    informal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anth
    -0.07
    -den
    -0.07
     नर
    -0.07
    Fat
    -0.07
     Ж
    -0.07
    .Ad
    -0.07
     Broadway
    -0.06
     achievements
    -0.06
     enviado
    -0.06
    TypeDef
    -0.06
    POSITIVE LOGITS
     stochastic
    0.06
    能
    0.06
     dokun
    0.06
     nokt
    0.06
     outer
    0.06
     Voting
    0.06
     tempor
    0.06
    ocomplete
    0.06
    ={{↵
    0.06
    .Sprintf
    0.06
    Act Density 0.033%

    No Known Activations