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

    Neuronpedia

    INDEX
    Explanations

    lack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åı³æīĭ
    -0.28
    继
    -0.27
    usi
    -0.27
     lig
    -0.26
    umbo
    -0.26
    è¾ĥ好
    -0.26
    ĤŃ
    -0.25
     train
    -0.25
    åħ»çĶŁ
    -0.25
     kad
    -0.25
    POSITIVE LOGITS
    æĹ¥æĬ¥éģĵ
    0.31
    çĻ¾èĬ±
    0.30
    Č↵
    0.30
    åŁĥå°Ķ
    0.28
    icular
    0.26
    beg
    0.26
    multipart
    0.25
    èĪ³
    0.25
    beros
    0.24
     Buen
    0.24
    Act Density 0.003%

    No Known Activations