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

    Neuronpedia

    INDEX
    Explanations

    branching and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findings
    0.82
    ing
    0.79
    ings
    0.71
     Findings
    0.69
    Findings
    0.66
    િંગ
    0.61
    sächlich
    0.61
    сіння
    0.61
     Fittings
    0.60
    Settings
    0.59
    POSITIVE LOGITS
    ton
    0.89
    redients
    0.85
    ly
    0.81
    ्ज
    0.80
     spree
    0.79
     prowess
    0.77
    tons
    0.69
     embers
    0.66
    redient
    0.66
     etiqu
    0.65
    Act Density 0.870%

    No Known Activations