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

    Neuronpedia

    INDEX
    Explanations

    list formatting instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    였
    0.57
    ственном
    0.55
    "]])
    0.54
    곸
    0.53
    widehat
    0.52
    或者
    0.52
    이고
    0.52
    colorbar
    0.51
    realpath
    0.51
    ாகவும்
    0.51
    POSITIVE LOGITS
     This
    1.05
     The
    0.96
     There
    0.93
     They
    0.89
    This
    0.85
     …
    0.84
    The
    0.82
    ;.
    0.82
     That
    0.80
     It
    0.78
    Act Density 0.023%

    No Known Activations