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

    Neuronpedia

    INDEX
    Explanations

    directory structures and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erture
    -0.07
    順
    -0.06
     UDP
    -0.06
    اپیم
    -0.06
    絵
    -0.06
    Chuck
    -0.06
     About
    -0.06
     cess
    -0.06
    iled
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     frosting
    0.07
     trouvé
    0.07
     протягом
    0.07
     {...
    0.06
    cooldown
    0.06
    (std
    0.06
    _publisher
    0.06
     reunited
    0.06
     Navy
    0.06
     Spl
    0.06
    Act Density 0.198%

    No Known Activations