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

    Neuronpedia

    INDEX
    Explanations

    lack of agency or responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     የስ
    0.49
     θε
    0.49
     하겠습니다
    0.48
    getRedTeam
    0.47
     တယ်
    0.45
     যে
    0.45
     рассказыва
    0.44
     tập
    0.44
     누가
    0.44
     beğen
    0.43
    POSITIVE LOGITS
    лью
    0.42
     induces
    0.42
    Expires
    0.42
     juris
    0.41
    শির
    0.41
    änner
    0.41
    ្នុង
    0.40
    ním
    0.40
     simpel
    0.39
     velike
    0.39
    Act Density 0.000%

    No Known Activations