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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本書
    -0.08
    וש
    -0.07
    lass
    -0.07
     suited
    -0.07
    _TITLE
    -0.06
    gens
    -0.06
     fellows
    -0.06
    Changed
    -0.06
     Levels
    -0.06
     headed
    -0.06
    POSITIVE LOGITS
     unpredictable
    0.07
     registros
    0.07
    "><?
    0.07
    ertificate
    0.06
    }/{
    0.06
    *i
    0.06
    -php
    0.06
     irregular
    0.06
    >')
    0.06
    冈
    0.06
    Act Density 0.027%

    No Known Activations