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

    Neuronpedia

    INDEX
    Explanations

    counsel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    power
    -0.07
    Peripheral
    -0.07
    _checks
    -0.07
     Wash
    -0.06
     Awards
    -0.06
    Strategy
    -0.06
    cord
    -0.06
    氣
    -0.06
    이자
    -0.06
     EVENT
    -0.06
    POSITIVE LOGITS
     assured
    0.07
    τερ
    0.06
    \-
    0.06
     Non
    0.06
    効
    0.06
    _Default
    0.06
     nợ
    0.06
     Boolean
    0.06
    爸
    0.06
     Yup
    0.06
    Act Density 0.004%

    No Known Activations