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

    Neuronpedia

    INDEX
    Explanations

    say "Base"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shin
    -0.07
     train
    -0.06
    تحض
    -0.06
    תו
    -0.06
    przedsiębiorc
    -0.06
     Sixth
    -0.06
    装备制造
    -0.06
    רך
    -0.06
    	position
    -0.06
     рук
    -0.06
    POSITIVE LOGITS
     adaptive
    0.07
    #{@
    0.07
    -small
    0.07
    [${
    0.07
     Paste
    0.07
     genotype
    0.07
    gross
    0.07
     swinger
    0.07
    egt
    0.07
    _quant
    0.07
    Act Density 0.007%

    No Known Activations