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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    フィール
    -0.08
    ZW
    -0.08
    runner
    -0.08
     arrives
    -0.07
    lear
    -0.07
    ไรก็ตาม
    -0.07
     recommendation
    -0.07
     ineffective
    -0.07
    _fold
    -0.07
     semblait
    -0.07
    POSITIVE LOGITS
    ਸ਼
    0.08
     incluem
    0.08
    الق
    0.08
     concerned
    0.08
    想到
    0.08
    ಿಂಗ್
    0.07
     عادة
    0.07
    ಿಂಗ
    0.07
     corretamente
    0.07
    كت
    0.07
    Act Density 0.018%

    No Known Activations