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

    Neuronpedia

    INDEX
    Explanations

    Filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tweaks
    -0.06
    _cookies
    -0.06
     Blade
    -0.06
    	damage
    -0.06
    .down
    -0.06
    aptured
    -0.06
     OBS
    -0.06
    REN
    -0.06
     Layers
    -0.06
     trợ
    -0.06
    POSITIVE LOGITS
    payer
    0.07
    ://'
    0.06
    .default
    0.06
    =in
    0.06
     AU
    0.06
    mvc
    0.06
    */↵↵↵
    0.06
    _TIM
    0.06
    =current
    0.06
    _lib
    0.06
    Act Density 0.025%

    No Known Activations