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

    Neuronpedia

    INDEX
    Explanations

    aj

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fre
    -0.07
    ['<{
    -0.06
    unsch
    -0.06
    (with
    -0.06
    Fant
    -0.06
    เส
    -0.06
    clado
    -0.06
     EGL
    -0.06
     SAN
    -0.06
     Méd
    -0.06
    POSITIVE LOGITS
     �
    0.06
    РСР
    0.06
    .pivot
    0.06
    .flink
    0.06
     kız
    0.06
    acb
    0.06
    vise
    0.06
     hale
    0.06
     pdb
    0.06
    高等
    0.06
    Act Density 0.000%

    No Known Activations