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

    Neuronpedia

    INDEX
    Explanations

    deliberately purposely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     notation
    -0.06
    .v
    -0.06
     Nam
    -0.06
     Greeks
    -0.06
    _OVERRIDE
    -0.06
    .activation
    -0.06
    appers
    -0.06
     Scenario
    -0.06
    Overview
    -0.06
     PCA
    -0.06
    POSITIVE LOGITS
     deliberately
    0.10
     purposely
    0.09
     intentionally
    0.08
     deliberate
    0.07
    entario
    0.07
    行動
    0.07
     gön
    0.07
     deben
    0.06
    行动
    0.06
     دشمن
    0.06
    Act Density 0.009%

    No Known Activations