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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    はじめに
    -0.66
    tapi
    -0.65
    gående
    -0.60
    HostException
    -0.59
    อ้างอิง
    -0.58
     Bate
    -0.56
    SourceChecksum
    -0.56
    ftagPool
    -0.56
    diging
    -0.56
     Erfolg
    -0.55
    POSITIVE LOGITS
    NamedQueries
    0.44
    Organisateur
    0.44
    Revenir
    0.43
    creativecommons
    0.42
    fromCharCode
    0.41
    AutoScaleMode
    0.41
    وعة
    0.39
     expressive
    0.39
    WithMany
    0.39
     creativa
    0.37
    Act Density 0.004%

    No Known Activations