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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that say something existed in one state but is subsequently changed to another state

    oai_token-act-pair · gemini-2.0-flash

    originally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evangelio
    -0.65
     виправивши
    -0.52
    cloudfront
    -0.51
     AssemblyTitle
    -0.47
    WebpackPlugin
    -0.47
    wai
    -0.47
     combinatie
    -0.46
     Wiktionnaire
    -0.45
     säll
    -0.45
    icol
    -0.44
    POSITIVE LOGITS
    undra
    0.65
    didSet
    0.57
     ProtoMessage
    0.57
    :✨
    0.56
    ClientSize
    0.55
    gulier
    0.54
     calendriers
    0.53
    itudinal
    0.53
     alert
    0.52
    PERTIES
    0.52
    Act Density 0.589%

    No Known Activations