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

    Neuronpedia

    INDEX
    Explanations

    set this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cryptocurrencies
    -0.07
    そ
    -0.06
    ustain
    -0.06
    Achie
    -0.06
    load
    -0.06
     dois
    -0.06
     dicho
    -0.06
    Span
    -0.06
    _ctrl
    -0.06
    Declared
    -0.06
    POSITIVE LOGITS
     پوست
    0.06
    ][_
    0.06
    ètres
    0.06
    ?):
    0.06
     handsome
    0.06
    럭
    0.06
     ΑΓ
    0.06
     Tales
    0.06
     interiors
    0.06
    ική
    0.06
    Act Density 0.016%

    No Known Activations