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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.77
    RenderAtEndOf
    -0.75
    __':
    -0.75
    Rhestr
    -0.75
    WriteTagHelper
    -0.70
    يميديا
    -0.69
     }}"></
    -0.67
    Хьажоргаш
    -0.66
     saites
    -0.65
    Breite
    -0.65
    POSITIVE LOGITS
    obis
    0.49
     t
    0.48
     working
    0.45
     keeping
    0.45
    WithIOException
    0.43
    meld
    0.43
     qui
    0.43
     qu
    0.42
     helping
    0.41
     ذ
    0.40
    Act Density 0.001%

    No Known Activations