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

    Neuronpedia

    INDEX
    Explanations

    FONT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -framework
    -0.08
     tenga
    -0.08
    -tag
    -0.07
     araç
    -0.07
     Garn
    -0.07
    垕
    -0.07
     valueForKey
    -0.07
    conda
    -0.07
     FetchType
    -0.07
    …but
    -0.07
    POSITIVE LOGITS
    싀
    0.07
    	stop
    0.07
    म
    0.07
    調查
    0.06
    מעניק
    0.06
    _expect
    0.06
     breakout
    0.06
     combos
    0.06
    យ
    0.06
     Cent
    0.06
    Act Density 0.000%

    No Known Activations