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

    Neuronpedia

    INDEX
    Explanations

    Senses and perception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frankie
    -0.08
     tgt
    -0.07
    472
    -0.06
    くる
    -0.06
     Stephen
    -0.06
     rms
    -0.06
    qw
    -0.06
    caler
    -0.06
     під
    -0.06
     Brandon
    -0.06
    POSITIVE LOGITS
    میل
    0.07
    Reg
    0.07
    िवस
    0.07
    Visualization
    0.06
    ootball
    0.06
    Into
    0.06
    _day
    0.06
    Strict
    0.06
    amik
    0.06
    ();?>
    0.06
    Act Density 0.052%

    No Known Activations