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

    Neuronpedia

    INDEX
    Explanations

    LH and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    —
    0.47
     کمک
    0.44
     leggere
    0.44
    ْن
    0.43
    ]),
    0.43
    gom
    0.43
    graphics
    0.43
    ],
    0.43
     graffiti
    0.42
    ।
    0.41
    POSITIVE LOGITS
    ocles
    0.44
     fdPar
    0.43
    AZ
    0.43
    또한
    0.42
     IEnumerator
    0.42
     ਇ
    0.42
    наче
    0.42
    onset
    0.41
    т
    0.41
     pastures
    0.41
    Act Density 0.001%

    No Known Activations