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

    Neuronpedia

    INDEX
    Explanations

    Role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ginger
    -0.07
     sensory
    -0.07
     Ges
    -0.06
     careg
    -0.06
     Lie
    -0.06
    transactions
    -0.06
     paste
    -0.06
    论
    -0.06
     minValue
    -0.06
     Ho
    -0.06
    POSITIVE LOGITS
     předsed
    0.06
    <select
    0.06
     книж
    0.06
     ال
    0.06
    //
    0.06
    Regardless
    0.06
    FAILURE
    0.06
     role
    0.06
    ":[
    0.06
    (primary
    0.06
    Act Density 0.006%

    No Known Activations