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

    Neuronpedia

    INDEX
    Explanations

    Sudan, Hungary, Hong Kong, conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orschung
    0.39
    ulture
    0.38
     dari
    0.37
    она
    0.37
    kim
    0.37
    I
    0.36
    uruan
    0.35
     our
    0.35
     companionship
    0.35
    с
    0.35
    POSITIVE LOGITS
     controvers
    0.52
     miatt
    0.45
     kvůli
    0.44
     universidades
    0.42
     akka
    0.42
     Zeitraum
    0.41
     الابتدائي
    0.40
     Einstellungen
    0.40
     exigir
    0.40
    できない
    0.40
    Act Density 0.078%

    No Known Activations