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

    Neuronpedia

    INDEX
    Explanations

    words starting with "Dr"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    www
    0.75
    vamente
    0.73
     whole
    0.73
     gel
    0.72
    ++++
    0.72
    窜
    0.71
    ರಿಯ
    0.70
     tú
    0.69
    ciones
    0.69
    Inj
    0.69
    POSITIVE LOGITS
    ifting
    1.19
    unken
    1.14
    ifter
    1.02
    astically
    0.97
    ifters
    0.96
    ุณ
    0.95
    acula
    0.92
    agan
    0.92
     sahab
    0.92
     Ambedkar
    0.90
    Act Density 0.040%

    No Known Activations