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

    Neuronpedia

    INDEX
    Explanations

    predictive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     말
    0.80
     début
    0.78
     Militar
    0.77
     efecto
    0.76
     केंद्रीय
    0.75
     vigil
    0.74
     bezeichnet
    0.74
     melted
    0.74
     CYP
    0.74
     milliers
    0.74
    POSITIVE LOGITS
    safe
    0.70
    artige
    0.65
    rinsic
    0.64
     offs
    0.64
    bage
    0.62
    ive
    0.62
    tio
    0.60
    sure
    0.60
     справед
    0.60
    neos
    0.60
    Act Density 0.013%

    No Known Activations