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

    Neuronpedia

    INDEX
    Explanations

    students and school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ases
    -0.54
     GenerationType
    -0.54
    っこう
    -0.50
    RouterModule
    -0.49
    IGO
    -0.48
     grans
    -0.47
     ols
    -0.46
    UnknownFields
    -0.46
    joi
    -0.45
    ISupport
    -0.45
    POSITIVE LOGITS
    PreferredItem
    0.73
    ItemBackground
    0.67
    uesday
    0.62
    Бахар
    0.60
     unknownFields
    0.58
    esterday
    0.57
    rinth
    0.56
     Roskov
    0.56
     actionMode
    0.55
    httphttps
    0.55
    Act Density 0.500%

    No Known Activations