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

    Neuronpedia

    INDEX
    Explanations

    events preceding or following actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afterlife
    0.85
     hacemos
    0.85
     كلهم
    0.84
     gesprek
    0.81
     maken
    0.79
     vogliamo
    0.78
     każdym
    0.77
     epitome
    0.77
    রাজন
    0.75
     klaar
    0.75
    POSITIVE LOGITS
    idespread
    0.92
     President
    0.88
     concerns
    0.87
     what
    0.84
     Operation
    0.83
     developments
    0.82
    Operation
    0.82
     widespread
    0.82
     criticisms
    0.81
     efforts
    0.80
    Act Density 0.171%

    No Known Activations