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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нні
    0.48
     الخلا
    0.47
     hablaremos
    0.46
     కోసం
    0.45
    სი
    0.44
     Осо
    0.44
     цю
    0.44
     Seite
    0.44
     ಇತರ
    0.43
    ací
    0.43
    POSITIVE LOGITS
    hubung
    0.38
     underm
    0.38
     decisions
    0.38
    ++;
    0.37
     salve
    0.37
     fentanyl
    0.37
     Albu
    0.36
    রাশ
    0.36
    hatan
    0.36
     opium
    0.36
    Act Density 0.001%

    No Known Activations