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

    Neuronpedia

    INDEX
    Explanations

    track identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lbl
    -0.07
     compile
    -0.07
     crane
    -0.06
     Handler
    -0.06
    胨
    -0.06
    -esteem
    -0.06
    emit
    -0.06
     graduates
    -0.06
    nextInt
    -0.06
     skilled
    -0.06
    POSITIVE LOGITS
     μ
    0.07
     j
    0.07
    เจอ
    0.07
    αι
    0.07
    !=
    0.06
     tonic
    0.06
    .dup
    0.06
    >d
    0.06
     стоим
    0.06
     certo
    0.06
    Act Density 0.006%

    No Known Activations