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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.68
    wiet
    -0.49
     tengamos
    -0.48
    Viitteet
    -0.47
     ligiloj
    -0.47
    retain
    -0.46
    webElementXpaths
    -0.46
     esternos
    -0.46
     Pieces
    -0.45
     sp
    -0.45
    POSITIVE LOGITS
    tagext
    0.76
     ExecuteAsync
    0.71
    able
    0.63
    neath
    0.62
    PYX
    0.61
    naments
    0.61
    western
    0.60
     للمعارف
    0.59
    extAlignment
    0.59
    🏼
    0.59
    Act Density 0.014%

    No Known Activations