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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     localize
    -0.07
     obstacles
    -0.07
     depletion
    -0.07
     municipalities
    -0.06
    (movie
    -0.06
     localization
    -0.06
     manipulation
    -0.06
     sopr
    -0.06
     religions
    -0.06
    [group
    -0.06
    POSITIVE LOGITS
    .FromSeconds
    0.07
     kotlin
    0.07
    zens
    0.06
     �
    0.06
     *,↵
    0.06
     Sms
    0.06
    ابل
    0.06
    mad
    0.06
    ’den
    0.06
    icons
    0.06
    Act Density 0.002%

    No Known Activations