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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depict
    -0.07
     Marcus
    -0.07
     Relative
    -0.06
    _Read
    -0.06
    Elements
    -0.06
     جم
    -0.06
     calculate
    -0.06
    anner
    -0.06
    应
    -0.06
    Ru
    -0.06
    POSITIVE LOGITS
    _avail
    0.07
     드
    0.07
    .getvalue
    0.06
    .EditValue
    0.06
     BITTE
    0.06
    ROPERTY
    0.06
     miệng
    0.06
    SCII
    0.06
    tod
    0.06
     العالمية
    0.06
    Act Density 0.128%

    No Known Activations