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

    Neuronpedia

    INDEX
    Explanations

    trigger and induction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    فاظ
    0.76
     opaque
    0.74
     ioutil
    0.71
     Allocation
    0.69
    ibik
    0.68
    っていく
    0.67
    াট
    0.66
    vency
    0.66
    Allocation
    0.66
     பட்டம்
    0.65
    POSITIVE LOGITS
     trigger
    3.88
     triggers
    3.76
    trigger
    3.60
     triggering
    3.59
     Trigger
    3.58
    Trigger
    3.50
     triggered
    3.37
    触发
    3.27
    triggers
    3.12
     TRIGGER
    2.95
    Act Density 0.728%

    No Known Activations