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

    Neuronpedia

    INDEX
    Explanations

    code examples and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     žal
    0.42
    ično
    0.40
    šnj
    0.39
     спустя
    0.38
     Após
    0.37
     осуществляется
    0.37
     αφού
    0.37
     डिस्क्रिप्शन
    0.37
     narrativa
    0.37
     üçüncü
    0.37
    POSITIVE LOGITS
    _{
    0.45
    '
    0.44
    ="
    0.39
    word
    0.38
    ct
    0.38
    ]
    0.38
     $\
    0.38
     '
    0.37
    c
    0.37
    $
    0.36
    Act Density 0.000%

    No Known Activations