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

    Neuronpedia

    INDEX
    Explanations

    Lord of the Rings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     politics
    -0.07
     exploring
    -0.07
     discre
    -0.07
     reopening
    -0.06
    This
    -0.06
     Douglas
    -0.06
    <Text
    -0.06
    انگلیسی
    -0.06
    Past
    -0.06
     payroll
    -0.06
    POSITIVE LOGITS
     SMS
    0.06
     ABS
    0.06
    _ble
    0.06
    polator
    0.06
    LocalizedString
    0.06
     contag
    0.06
     ParameterDirection
    0.06
    fec
    0.06
    ौत
    0.06
    рач
    0.06
    Act Density 0.007%

    No Known Activations