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

    Neuronpedia

    INDEX
    Explanations

    aro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    śni
    -0.08
    неж
    -0.07
    .Normalize
    -0.07
    泥土
    -0.07
    	xml
    -0.07
    美味しい
    -0.07
    变成
    -0.07
    ('-',
    -0.07
    лё
    -0.07
    行使
    -0.07
    POSITIVE LOGITS
    鹕
    0.07
    _buff
    0.07
    Stopped
    0.07
    _ir
    0.07
     Forbes
    0.06
     Allow
    0.06
    .multi
    0.06
     achievements
    0.06
     دولار
    0.06
     adjustment
    0.06
    Act Density 0.001%

    No Known Activations