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

    Neuronpedia

    INDEX
    Explanations

    /ajax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nii
    -0.09
    Tickets
    -0.08
    Tick
    -0.07
     Nhi
    -0.07
    吨
    -0.07
    Editar
    -0.07
    广汽
    -0.07
    .getAttribute
    -0.07
    	btn
    -0.07
    _PR
    -0.07
    POSITIVE LOGITS
     husbands
    0.07
     arena
    0.07
    任何人
    0.06
    ALE
    0.06
    ale
    0.06
     الخارجية
    0.06
     example
    0.06
    ocs
    0.06
    	column
    0.06
     Essays
    0.06
    Act Density 0.001%

    No Known Activations