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

    Neuronpedia

    INDEX
    Explanations

    aimed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -0.69
    expandindo
    -0.68
    Extinguishing
    -0.65
     Waray
    -0.61
     مرئيه
    -0.61
     endwhile
    -0.59
    UIControlState
    -0.59
    ">//
    -0.59
    WARDS
    -0.58
    wards
    -0.57
    POSITIVE LOGITS
    poir
    0.47
    omitempty
    0.47
     ModelExpression
    0.43
    jsonwebtoken
    0.41
    temon
    0.41
    ayı
    0.40
    ><?
    0.40
    Takes
    0.40
    象
    0.39
     Ekiti
    0.39
    Act Density 0.001%

    No Known Activations