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

    Neuronpedia

    INDEX
    Explanations

    root

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    -0.07
    77
    -0.07
     hotter
    -0.06
    anoia
    -0.06
     Anyone
    -0.06
    #__
    -0.06
    下的
    -0.06
    _provider
    -0.06
    -written
    -0.06
    POSITIVE LOGITS
    _FINE
    0.07
     Exiting
    0.07
    êtes
    0.06
    Coordinates
    0.06
    (GameObject
    0.06
     Sinn
    0.06
    ес
    0.06
    인증
    0.06
     Responsive
    0.06
    тура
    0.06
    Act Density 0.017%

    No Known Activations