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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sing
    -0.07
     toJSON
    -0.07
    fullscreen
    -0.06
     túi
    -0.06
     <=>
    -0.06
    	last
    -0.06
     Harvey
    -0.06
    inn
    -0.06
    _PT
    -0.06
     executable
    -0.06
    POSITIVE LOGITS
    elly
    0.06
    .newLine
    0.06
    nen
    0.06
     норматив
    0.06
     privile
    0.06
    /NĐ
    0.06
     MediaTek
    0.06
    oppel
    0.06
     tuy
    0.05
    民主
    0.05
    Act Density 0.056%

    No Known Activations