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

    Neuronpedia

    INDEX
    Explanations

    technical context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শুরুতে
    0.60
    চিত্রে
    0.60
    ведении
    0.60
    𒄷
    0.56
     Medell
    0.55
     osoba
    0.55
    incia
    0.55
     automobile
    0.54
    ទទ
    0.54
    OCKED
    0.54
    POSITIVE LOGITS
    lit
    0.59
    Never
    0.59
    little
    0.59
    순
    0.58
    routine
    0.55
    Hits
    0.54
    Quad
    0.54
    Storm
    0.53
    思想
    0.52
     hits
    0.52
    Act Density 0.001%

    No Known Activations