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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erosis
    -0.06
     stamped
    -0.06
    EZ
    -0.06
    .onclick
    -0.06
    اذ
    -0.06
    gz
    -0.06
    menin
    -0.06
     tiene
    -0.06
    ト
    -0.05
     Larson
    -0.05
    POSITIVE LOGITS
    (chars
    0.07
    Arrow
    0.06
     pore
    0.06
     cung
    0.06
    ynchronous
    0.06
     educated
    0.06
    (power
    0.06
     输
    0.06
    �
    0.06
     una
    0.06
    Act Density 0.000%

    No Known Activations