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

    Neuronpedia

    INDEX
    Explanations

    ind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Healthy
    -0.07
    dense
    -0.07
     trail
    -0.06
    Den
    -0.06
    -0.06
    düm
    -0.06
    attering
    -0.06
    .sourceforge
    -0.06
    353
    -0.06
    _rename
    -0.06
    POSITIVE LOGITS
     beginners
    0.07
    又
    0.06
     wes
    0.06
     आस
    0.06
     aos
    0.06
     final
    0.06
     عام
    0.06
    _FINAL
    0.06
     EVT
    0.06
     uLocal
    0.06
    Act Density 0.005%

    No Known Activations