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

    Neuronpedia

    INDEX
    Explanations

    voodoo and reef

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.66
    ной
    0.58
    俣
    0.57
    ஞர்
    0.56
    line
    0.54
    ad
    0.52
    τή
    0.50
     прове
    0.49
    ä
    0.48
    ücher
    0.48
    POSITIVE LOGITS
     auraient
    0.64
    𝑯
    0.63
     aile
    0.60
    𝓹
    0.58
    ร้าน
    0.57
    ylmethyl
    0.54
     shank
    0.54
     hamp
    0.52
    huang
    0.52
    ع
    0.52
    Act Density 0.000%

    No Known Activations