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

    Neuronpedia

    INDEX
    Explanations

    mus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     */;↵
    -0.07
     patched
    -0.07
    .Validate
    -0.06
     Hou
    -0.06
    SpecWarn
    -0.06
    $path
    -0.06
     наруж
    -0.06
     staircase
    -0.06
    ıma
    -0.06
    Fade
    -0.06
    POSITIVE LOGITS
    -з
    0.07
    TEMPL
    0.06
     мус
    0.06
     обл
    0.06
     TERM
    0.06
     Islamic
    0.06
     Ville
    0.06
    _SUBJECT
    0.06
    Mind
    0.06
     artistic
    0.06
    Act Density 0.003%

    No Known Activations