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

    Neuronpedia

    INDEX
    Explanations

    dangerous activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raj
    0.50
    AP
    0.45
    Partner
    0.44
    uda
    0.43
     NPs
    0.43
     کنگ
    0.43
    tet
    0.42
    tingen
    0.41
    Contract
    0.41
    {\
    0.41
    POSITIVE LOGITS
    elevationMap
    0.55
    苋
    0.54
    انس
    0.51
    填写
    0.51
    谯
    0.51
    ाइन
    0.50
    无需
    0.50
     startDate
    0.49
     አይደ
    0.49
    条件下
    0.49
    Act Density 0.000%

    No Known Activations