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

    Neuronpedia

    INDEX
    Explanations

    visual descriptions and art styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пред
    0.45
    पृ
    0.42
    ॉर्ड
    0.41
    мере
    0.41
    風險
    0.38
    ऋ
    0.38
     cuáles
    0.38
    ९
    0.38
    风险
    0.37
     चिकित्स
    0.37
    POSITIVE LOGITS
     Nodo
    0.43
     conical
    0.41
    Helmet
    0.41
     choline
    0.40
     moustache
    0.38
    endtime
    0.38
     Steel
    0.38
     chassis
    0.38
     Plum
    0.38
    zinha
    0.37
    Act Density 0.007%

    No Known Activations