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

    Neuronpedia

    INDEX
    Explanations

    file operations and decompression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SHALL
    0.39
     vésicules
    0.38
     plă
    0.37
     imidazol
    0.36
    ائم
    0.35
     entram
    0.35
     Städte
    0.35
     perí
    0.34
     cellules
    0.34
     methylene
    0.34
    POSITIVE LOGITS
    os
    0.46
    #
    0.43
    or
    0.42
    さて
    0.41
    in
    0.40
    acas
    0.40
    """
    0.40
    Q
    0.39
    async
    0.37
    arbeit
    0.37
    Act Density 0.090%

    No Known Activations