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

    Neuronpedia

    INDEX
    Explanations

    death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pes
    -0.07
    _AdjustorThunk
    -0.07
    _Project
    -0.06
    _CP
    -0.06
    Attendance
    -0.06
     Fraser
    -0.06
    sizeof
    -0.06
     Division
    -0.06
    ')):↵
    -0.06
     adaptable
    -0.06
    POSITIVE LOGITS
    feld
    0.06
     facing
    0.06
     FCC
    0.06
    normalize
    0.06
    训
    0.06
    removeClass
    0.06
    ::_('
    0.06
     untouched
    0.06
    mal
    0.06
    须
    0.06
    Act Density 0.000%

    No Known Activations