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

    Neuronpedia

    INDEX
    Explanations

    happened

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    credited
    -0.07
     economist
    -0.06
     linger
    -0.06
    Venue
    -0.06
     yetiş
    -0.06
    obao
    -0.06
    akers
    -0.06
     innoc
    -0.06
    /button
    -0.06
     Nixon
    -0.06
    POSITIVE LOGITS
     libre
    0.07
    خدام
    0.06
    0.06
     europ
    0.06
    cup
    0.06
    AMA
    0.06
    φυ
    0.06
    fc
    0.06
    .au
    0.06
    achusetts
    0.06
    Act Density 0.000%

    No Known Activations