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

    Neuronpedia

    INDEX
    Explanations

    addition to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ë¦Ħ
    -0.09
    _algo
    -0.09
    acman
    -0.09
     lẽ
    -0.09
    usz
    -0.09
     grooming
    -0.09
    atty
    -0.08
    dens
    -0.08
    ắc
    -0.08
     Chow
    -0.08
    POSITIVE LOGITS
    ality
    0.13
    nal
    0.12
     to
    0.12
    ätzlich
    0.11
    itionally
    0.11
     insult
    0.10
    al
    0.10
    ally
    0.10
     Gol
    0.10
     pig
    0.10
    Act Density 0.003%

    No Known Activations