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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iprot
    -0.69
    parseFrom
    -0.63
     Lijst
    -0.59
    atorul
    -0.59
    AccessorTable
    -0.59
    XmlAccessType
    -0.57
    batore
    -0.57
    RUnlock
    -0.57
     StringTokenizer
    -0.57
     otomatig
    -0.56
    POSITIVE LOGITS
     متعلقه
    0.54
     defaultstate
    0.48
    __]
    0.46
    elemField
    0.45
     dúvidas
    0.44
     hiasan
    0.43
     dormitorios
    0.42
    StoryboardSegue
    0.42
    Données
    0.42
     innehå
    0.41
    Act Density 0.004%

    No Known Activations