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

    Neuronpedia

    INDEX
    Explanations

    captured transferred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     QtGui
    -0.52
     GenerationType
    -0.51
    makedirs
    -0.49
    handelt
    -0.49
    getWriter
    -0.48
    badlogic
    -0.46
    hnung
    -0.45
    ❋
    -0.45
     AspNetCore
    -0.44
     ddelweddau
    -0.44
    POSITIVE LOGITS
    UserScript
    0.73
    RectangleBorder
    0.66
    ContentAlignment
    0.64
     viață
    0.64
    ühungen
    0.64
    InputBorder
    0.60
     precisione
    0.59
     pagină
    0.58
    ftagPool
    0.57
    Personendaten
    0.57
    Act Density 0.066%

    No Known Activations