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

    Neuronpedia

    INDEX
    Explanations

    provocation and provocative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.05
    ла
    0.85
    esian
    0.79
     Ayurvedic
    0.78
    па
    0.78
    ことを
    0.77
    CA
    0.77
    phosphat
    0.75
    MA
    0.75
    MIN
    0.75
    POSITIVE LOGITS
     provocative
    1.05
     provoke
    1.04
     provocation
    0.93
    of
    0.93
     provoking
    0.91
     provoc
    0.89
     provocar
    0.88
    其他
    0.87
     provoca
    0.84
     provoked
    0.83
    Act Density 0.005%

    No Known Activations