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

    Neuronpedia

    INDEX
    Explanations

    block diagram or related entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.19
    c
    1.05
    the
    0.98
    but
    0.97
    br
    0.94
    л
    0.93
    h
    0.91
    f
    0.91
    bh
    0.88
    이었
    0.87
    POSITIVE LOGITS
     for
    1.12
    م
    1.00
    ي
    0.94
     Blocks
    0.90
     on
    0.80
    يّ
    0.79
     blocks
    0.77
     Block
    0.75
     Modo
    0.75
    ে
    0.75
    Act Density 0.194%

    No Known Activations