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

    Neuronpedia

    INDEX
    Explanations

    **Enum and specific objects/terms**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.96
    ᡵ
    0.94
    fic
    0.94
    ya
    0.90
    უფ
    0.90
    pher
    0.88
    fh
    0.88
    いま
    0.86
    næ
    0.85
    fpr
    0.84
    POSITIVE LOGITS
    تے
    1.13
     prescribes
    0.95
     substantiate
    0.89
    EEEE
    0.87
     himself
    0.86
     postulate
    0.86
     dislocations
    0.86
    EK
    0.85
     lié
    0.84
     enforces
    0.84
    Act Density 0.005%

    No Known Activations