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

    Neuronpedia

    INDEX
    Explanations

    built with images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विशेष
    0.36
    fte
    0.36
    ofi
    0.36
    oport
    0.34
    setting
    0.34
    е
    0.34
    betrieb
    0.33
    aufen
    0.33
    фта
    0.33
    ال
    0.32
    POSITIVE LOGITS
     egli
    0.43
     professe
    0.40
    美国的
    0.40
     udało
    0.38
     igualdad
    0.38
     विद्यालयों
    0.38
     hígado
    0.38
     języ
    0.38
    کریاں
    0.37
     princesses
    0.37
    Act Density 0.001%

    No Known Activations