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

    Neuronpedia

    INDEX
    Explanations

    HTML lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alloween
    -0.06
    !
    -0.06
    rored
    -0.06
     Keystone
    -0.06
    での
    -0.06
    utron
    -0.06
    ?page
    -0.06
    Bindings
    -0.06
    ateral
    -0.06
    เหน
    -0.06
    POSITIVE LOGITS
    responses
    0.07
     RGBA
    0.07
     nada
    0.07
     Eden
    0.06
    Identification
    0.06
     GC
    0.06
    ')
↵
↵
    0.06
     danger
    0.06
     closeModal
    0.06
     agile
    0.06
    Act Density 0.002%

    No Known Activations