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

    Neuronpedia

    INDEX
    Explanations

    REF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toaster
    -0.07
     te
    -0.07
     bacter
    -0.07
    행위
    -0.07
     quar
    -0.07
     đàn
    -0.07
    _ctx
    -0.07
     anyone
    -0.07
     bu
    -0.06
     picked
    -0.06
    POSITIVE LOGITS
    :absolute
    0.09
    toFloat
    0.08
    ӛ
    0.08
    ↡
    0.07
    .componentInstance
    0.07
    ellant
    0.07
     borderTop
    0.07
    ikhail
    0.07
    把自己的
    0.07
    湝
    0.07
    Act Density 0.101%

    No Known Activations