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
    -loving
    -0.09
     aimé
    -0.08
     själva
    -0.08
     seconda
    -0.08
     λόγω
    -0.08
     aufgrund
    -0.08
     ঘটে
    -0.07
     lovers
    -0.07
     sorr
    -0.07
     VC
    -0.07
    POSITIVE LOGITS
     corrective
    0.09
     remedy
    0.09
     pomocą
    0.09
     adjustable
    0.09
    adjust
    0.08
     көм
    0.08
     antid
    0.08
    调整
    0.08
    ことで
    0.08
     adjustment
    0.08
    Act Density 0.018%

    No Known Activations