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

    Neuronpedia

    INDEX
    Explanations

    quirky memorable distinctive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.24
    .
    0.22
    ."
    0.19
    .\
    0.18
    ).
    0.18
    .)
    0.18
    ".
    0.18
    ().
    0.17
     of
    0.17
    .]
    0.17
    POSITIVE LOGITS
     catchy
    0.18
     flashy
    0.18
     quirky
    0.18
     hefty
    0.18
     sassy
    0.17
     blatant
    0.17
     motivational
    0.17
    कुछ
    0.17
     பல்வேறு
    0.17
     crafty
    0.17
    Act Density 0.000%

    No Known Activations