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

    Neuronpedia

    INDEX
    Explanations

    personal problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bonus
    -0.08
     bonuses
    -0.08
     Operand
    -0.08
    voet
    -0.08
     Bonus
    -0.08
     बोनस
    -0.08
     odo
    -0.08
     Ore
    -0.08
     blush
    -0.07
    "]
↵
    -0.07
    POSITIVE LOGITS
     uphe
    0.09
     turmoil
    0.09
    Transitions
    0.09
     drama
    0.09
     circunstancias
    0.08
     emoc
    0.08
     divorce
    0.08
    Conc
    0.08
     sophomore
    0.08
    Drama
    0.08
    Act Density 0.037%

    No Known Activations