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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kein
    -0.08
    紙
    -0.07
     wides
    -0.07
    .sf
    -0.07
    'aut
    -0.07
     kaf
    -0.06
     reb
    -0.06
    _requires
    -0.06
     Sarah
    -0.06
     Personnel
    -0.06
    POSITIVE LOGITS
    เกษตร
    0.06
    antage
    0.06
    roll
    0.06
    تق
    0.06
    055
    0.06
    	title
    0.06
    (mContext
    0.06
     glad
    0.06
    .В
    0.06
    _cancel
    0.06
    Act Density 0.000%

    No Known Activations