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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _To
    -0.08
     defeated
    -0.06
     شوند
    -0.06
    handles
    -0.06
    umba
    -0.06
    spacer
    -0.06
    _deriv
    -0.06
    .Username
    -0.06
     lug
    -0.06
    (wp
    -0.06
    POSITIVE LOGITS
     �
    0.06
    enes
    0.06
    (Game
    0.06
     premature
    0.06
    ,
    0.06
    -using
    0.06
     coined
    0.06
    น
    0.06
    umen
    0.05
    <uint
    0.05
    Act Density 0.000%

    No Known Activations