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

    Neuronpedia

    INDEX
    Explanations

    goal hijacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ingrained
    0.41
     машине
    0.40
     의
    0.39
    ственных
    0.39
     сен
    0.39
     ইঙ্গিত
    0.38
    ffect
    0.38
     ставка
    0.38
     Einstellungen
    0.37
     enveloped
    0.37
    POSITIVE LOGITS
     copol
    0.43
     zob
    0.42
     എം
    0.39
    यदि
    0.39
     arrowhead
    0.39
    IAS
    0.39
     lexicon
    0.38
    ۋ
    0.38
    ڍ
    0.37
    گیر
    0.37
    Act Density 0.000%

    No Known Activations