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

    Neuronpedia

    INDEX
    Explanations

    first person narration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ss
    -0.07
    .problem
    -0.07
     кг
    -0.07
    .Params
    -0.07
    ,float
    -0.07
    ope
    -0.07
    (exp
    -0.07
    科学
    -0.07
     зуст
    -0.06
    یط
    -0.06
    POSITIVE LOGITS
     readdir
    0.07
     merciless
    0.06
     мом
    0.06
     deadlines
    0.06
     INSTANCE
    0.06
     δυνα
    0.06
     faucet
    0.06
     Generic
    0.05
    listen
    0.05
     presence
    0.05
    Act Density 0.077%

    No Known Activations