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

    Neuronpedia

    INDEX
    Explanations

    scandal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bleak
    -0.08
     Bethlehem
    -0.07
     motion
    -0.07
     chiế
    -0.07
     běž
    -0.07
     WB
    -0.07
     TARGET
    -0.07
     اروپ
    -0.07
     mnemonic
    -0.06
     тобі
    -0.06
    POSITIVE LOGITS
     scandal
    0.19
     scandals
    0.14
    andal
    0.09
     industry
    0.07
     hashtag
    0.07
     scam
    0.07
     conducting
    0.06
     testimony
    0.06
    851
    0.06
    aston
    0.06
    Act Density 0.003%

    No Known Activations