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

    Neuronpedia

    INDEX
    Explanations

    any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    իս
    0.75
    Yes
    0.74
    umen
    0.74
    cash
    0.73
    unt
    0.72
     cash
    0.71
     required
    0.70
    yes
    0.68
    ios
    0.67
     نہیں۔
    0.66
    POSITIVE LOGITS
     anys
    0.99
     Any
    0.94
    Any
    0.94
     any
    0.84
     ANY
    0.83
     qualquer
    0.80
    Anyway
    0.79
     कोणत्याही
    0.79
     amy
    0.78
     Qualquer
    0.76
    Act Density 0.000%

    No Known Activations