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

    Neuronpedia

    INDEX
    Explanations

    technical topics/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    كويكب
    -0.64
    AccessorTable
    -0.54
     himo
    -0.50
    berra
    -0.48
     mission
    -0.48
     مرئيه
    -0.48
     FishBase
    -0.47
    InjectAttribute
    -0.47
    nodoc
    -0.47
    MergeFrom
    -0.46
    POSITIVE LOGITS
     âgé
    0.54
     prêts
    0.54
    isering
    0.52
     pacchetto
    0.52
     jambes
    0.52
    understanding
    0.52
     pioggia
    0.51
     âgées
    0.51
    orianCalendar
    0.51
     couvercle
    0.51
    Act Density 0.001%

    No Known Activations