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

    Neuronpedia

    INDEX
    Explanations

    gatsby, cite, fancy, vite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    infodisc
    0.42
     აქვს
    0.42
    setWalk
    0.41
    goài
    0.41
     thisTrack
    0.40
     состава
    0.40
    dpy
    0.40
     üld
    0.40
    აგ
    0.39
    anneled
    0.39
    POSITIVE LOGITS
     acquire
    0.38
    如果不
    0.37
    如果
    0.36
    plugin
    0.35
     plugin
    0.35
    ire
    0.35
     comb
    0.35
    acquire
    0.34
    (=
    0.34
     if
    0.33
    Act Density 0.000%

    No Known Activations