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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fc
    -0.07
     delta
    -0.07
     CircularProgress
    -0.06
     acc
    -0.06
     부
    -0.06
    (contract
    -0.06
    _REF
    -0.06
     όπου
    -0.06
    [type
    -0.06
    ffa
    -0.06
    POSITIVE LOGITS
     Ссылки
    0.07
    inoa
    0.06
    .onCreate
    0.06
    گیری
    0.06
    드로
    0.06
     Rather
    0.06
    /*!
    0.06
    PELL
    0.06
    uddenly
    0.06
     Exped
    0.06
    Act Density 0.000%

    No Known Activations