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

    Neuronpedia

    INDEX
    Explanations

    generality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IGH
    -0.06
     بخ
    -0.06
    .flags
    -0.06
     ￣
    -0.06
     hamburg
    -0.06
    tolua
    -0.06
    pto
    -0.06
    $',
    -0.06
     beauty
    -0.06
     zákaz
    -0.06
    POSITIVE LOGITS
    ลำ
    0.07
     inspiration
    0.07
     extravagant
    0.07
     нек
    0.06
    ὰ
    0.06
    ISBN
    0.06
    	curl
    0.06
     ISBN
    0.06
     हत
    0.06
    _combined
    0.06
    Act Density 0.002%

    No Known Activations