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

    Neuronpedia

    INDEX
    Explanations

    override

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nemidophorus
    0.78
    FORMATION
    0.78
    味料
    0.77
    iti
    0.76
     particulières
    0.75
    合物
    0.75
    bersihan
    0.74
    ❧
    0.74
    ipitation
    0.73
    ລະ
    0.73
    POSITIVE LOGITS
     toto
    0.81
     tannins
    0.79
     pink
    0.78
     sni
    0.75
     forced
    0.75
     increased
    0.74
     rosy
    0.73
     homogen
    0.73
     roost
    0.73
     gastric
    0.72
    Act Density 0.001%

    No Known Activations