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

    Neuronpedia

    INDEX
    Explanations

    code division operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    anee
    -0.07
    ーズ
    -0.07
    ould
    -0.07
    举办
    -0.07
    üz
    -0.07
    orse
    -0.07
     konnten
    -0.07
    ukan
    -0.07
     membranes
    -0.07
    POSITIVE LOGITS
     кислот
    0.09
     cast
    0.09
     হিস
    0.09
     casts
    0.09
    _cast
    0.09
     ари
    0.09
     rounding
    0.08
     absorbs
    0.08
     sais
    0.08
     અકસ્માત
    0.08
    Act Density 0.005%
    No Known Activations