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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    **↵
    -0.08
     dabei
    -0.07
     Flame
    -0.06
    ()))↵
    -0.06
     freedom
    -0.06
    无法
    -0.06
    Characteristic
    -0.06
     Editor
    -0.06
    	Start
    -0.06
    '",↵
    -0.06
    POSITIVE LOGITS
     düşük
    0.08
    _YELLOW
    0.07
    apple
    0.07
    iliary
    0.07
    vailable
    0.07
    isel
    0.07
    createQuery
    0.06
    partition
    0.06
    ORIZATION
    0.06
    wf
    0.06
    Act Density 0.032%

    No Known Activations