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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.62
    __":
    -0.60
    bootstrapcdn
    -0.60
     démocr
    -0.59
    LookAnd
    -0.58
     étrang
    -0.57
     visibilité
    -0.57
     onOptions
    -0.57
     étoient
    -0.56
    neté
    -0.56
    POSITIVE LOGITS
    webElementGuid
    0.56
     e
    0.54
     pat
    0.54
     é
    0.51
    verwijspagina
    0.50
    vedic
    0.50
    soft
    0.48
     circulated
    0.48
    protoimpl
    0.48
    
    0.47
    Act Density 0.001%

    No Known Activations