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

    Neuronpedia

    INDEX
    Explanations

    Nationalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isset
    -0.06
     overthrow
    -0.06
    oooooooo
    -0.06
     posX
    -0.06
    _counters
    -0.06
    aktion
    -0.06
    richText
    -0.06
     kill
    -0.06
    tfoot
    -0.06
    .xlabel
    -0.06
    POSITIVE LOGITS
    eshire
    0.07
     возду
    0.07
     باشند
    0.07
     Гер
    0.07
     prod
    0.07
    _feats
    0.07
    イス
    0.07
    .ir
    0.06
    -dir
    0.06
     Chief
    0.06
    Act Density 0.017%

    No Known Activations