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

    Neuronpedia

    INDEX
    Explanations

    code examples and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อม
    0.35
    兰
    0.34
    orn
    0.33
     palust
    0.31
    Allemagne
    0.31
    lü
    0.30
    luk
    0.30
    zhu
    0.30
     رست
    0.30
    ha
    0.30
    POSITIVE LOGITS
     également
    0.43
     novamente
    0.42
     again
    0.39
     nuevamente
    0.38
     CMakeFiles
    0.37
     also
    0.37
     ebenfalls
    0.36
     Again
    0.35
     Также
    0.35
     также
    0.35
    Act Density 0.039%

    No Known Activations