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

    Neuronpedia

    INDEX
    Explanations

    hustle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evapor
    -0.07
     drm
    -0.07
    �
    -0.06
    Gun
    -0.06
    什么东西
    -0.06
    末
    -0.06
    itespace
    -0.06
     document
    -0.06
     arrogant
    -0.06
    ･･･
    -0.06
    POSITIVE LOGITS
     kontrol
    0.07
     🙂↵↵
    0.07
    _(
    0.07
     reputation
    0.07
    BackPressed
    0.07
     Decide
    0.07
     humility
    0.07
    (query
    0.07
     Payload
    0.07
    flate
    0.07
    Act Density 0.025%

    No Known Activations