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

    Neuronpedia

    INDEX
    Explanations

    short alphanumeric identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ပြော
    0.30
     Zone
    0.30
     McDonnell
    0.30
    zón
    0.30
     Ground
    0.29
     Bells
    0.29
     Normandy
    0.29
     Шо
    0.29
     निर्णया
    0.29
     Pollock
    0.28
    POSITIVE LOGITS
     tingkat
    0.31
     dient
    0.31
     bhikkhave
    0.30
    Via
    0.29
    उन्होंने
    0.29
     abogado
    0.29
     specialise
    0.29
    setFixedHeight
    0.29
     karde
    0.29
     consultez
    0.28
    Act Density 0.006%

    No Known Activations