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

    Neuronpedia

    INDEX
    Explanations

    intentionally harmful actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dü
    -0.09
     automatically
    -0.09
    orage
    -0.09
    awy
    -0.09
     automatic
    -0.09
    -deals
    -0.09
    coe
    -0.09
    elier
    -0.09
    뢰
    -0.08
    /new
    -0.08
    POSITIVE LOGITS
     effort
    0.12
    /un
    0.11
    inka
    0.10
    fully
    0.10
     afore
    0.10
    /man
    0.10
     seek
    0.09
     obt
    0.09
     efforts
    0.09
    /random
    0.09
    Act Density 0.035%

    No Known Activations