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

    Neuronpedia

    INDEX
    Explanations

    Annual policy and operational reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cosine
    0.46
     hyperbolic
    0.39
     grotesque
    0.38
     combination
    0.37
     galactic
    0.36
     countries
    0.36
     galaxy
    0.36
     poetic
    0.36
     intersected
    0.36
     chorus
    0.35
    POSITIVE LOGITS
     Licenses
    0.71
     licenses
    0.66
     Payroll
    0.66
    Licenses
    0.64
     cybersecurity
    0.61
     invoicing
    0.61
     payroll
    0.61
    Security
    0.61
     Finances
    0.61
     безопасности
    0.60
    Act Density 0.027%

    No Known Activations