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

    Neuronpedia

    INDEX
    Explanations

    watch and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.40
    ifting
    1.09
     войск
    1.02
    of
    1.00
     pasukan
    0.99
     повинні
    0.96
    ación
    0.96
    ués
    0.95
    ından
    0.94
     Quadrupèdes
    0.93
    POSITIVE LOGITS
    c
    1.61
    க்கு
    1.56
    n
    1.53
    ن
    1.41
    p
    1.40
    ية
    1.38
    נ
    1.31
    ד
    1.31
    தி
    1.23
    দের
    1.22
    Act Density 0.014%

    No Known Activations