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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ださい
    -0.07
     timeless
    -0.07
    _successful
    -0.07
     Ґ
    -0.07
     seeks
    -0.07
     hatred
    -0.07
    GORITH
    -0.07
    ایی
    -0.06
    _req
    -0.06
     repeatedly
    -0.06
    POSITIVE LOGITS
    ]){↵
    0.06
    ิม
    0.06
     dé
    0.06
    стан
    0.06
    '))
    0.06
     steht
    0.06
    .',
    0.06
    \
↵
    0.06
    bd
    0.06
    fight
    0.06
    Act Density 0.059%

    No Known Activations