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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rock
    -0.07
     parasites
    -0.06
     trad
    -0.06
     h
    -0.06
    .GetName
    -0.06
    _runtime
    -0.06
     століття
    -0.06
     repetitive
    -0.06
    Rock
    -0.06
    _guard
    -0.06
    POSITIVE LOGITS
    nilai
    0.06
     mới
    0.06
    rika
    0.06
    ificacion
    0.06
    ilia
    0.06
    ject
    0.05
    няет
    0.05
     нарез
    0.05
    яв
    0.05
     nebyla
    0.05
    Act Density 0.108%

    No Known Activations