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

    Neuronpedia

    INDEX
    Explanations

    donations or gravity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zenith
    0.54
     ZEN
    0.52
    笹
    0.52
     datasheet
    0.52
     concisely
    0.51
    ziehen
    0.50
     matem
    0.49
     estatales
    0.49
     Watan
    0.48
     പോലീസ്
    0.48
    POSITIVE LOGITS
    am
    0.45
    ات
    0.42
    environments
    0.41
    0.39
    arre
    0.38
    нями
    0.38
    Range
    0.38
     шко
    0.38
     کو
    0.38
    ou
    0.37
    Act Density 0.000%

    No Known Activations