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

    Neuronpedia

    INDEX
    Explanations

    _fmt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Meter
    -0.09
    _meter
    -0.08
     Blackburn
    -0.08
     deden
    -0.08
    (loss
    -0.08
    াধ্যম
    -0.08
    ариф
    -0.08
    �
    -0.08
    نمای
    -0.08
    Decoder
    -0.08
    POSITIVE LOGITS
     ves
    0.08
     maturity
    0.08
     hus
    0.08
     ms
    0.08
     സ്ഥിര
    0.08
     atract
    0.07
     stability
    0.07
     jira
    0.07
     estabilidad
    0.07
     estabilidade
    0.07
    Act Density 0.000%

    No Known Activations