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

    Neuronpedia

    INDEX
    Explanations

    dll imports and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    1.05
     be
    0.96
     are
    0.90
     OPP
    0.85
     suffrage
    0.84
     reggae
    0.84
     giày
    0.84
     kebab
    0.82
    :
    0.82
     can
    0.81
    POSITIVE LOGITS
    ip
    1.15
    u
    0.94
    l
    0.90
    b
    0.88
    ng
    0.88
    that
    0.86
    ков
    0.82
    d
    0.82
    pl
    0.81
    man
    0.80
    Act Density 0.000%

    No Known Activations