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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ه
    -0.74
     rodríguez
    -0.69
    >{@
    -0.65
    ת
    -0.58
    Referencies
    -0.56
     oliveira
    -0.56
    tty
    -0.54
    teiro
    -0.54
    ی
    -0.53
    tdata
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    0.79
    eyes
    0.63
    ever
    0.62
    InjectAttribute
    0.59
    eye
    0.57
    ets
    0.55
    NOPQRST
    0.55
     '\\;'
    0.53
    ept
    0.52
    ed
    0.50
    Act Density 0.070%

    No Known Activations