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

    Neuronpedia

    INDEX
    Explanations

    Controversial topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hao
    -0.08
     toes
    -0.07
     calcium
    -0.07
     formulations
    -0.07
     nudity
    -0.06
     textColor
    -0.06
     Ale
    -0.06
     cessation
    -0.06
    iations
    -0.06
    LOCITY
    -0.06
    POSITIVE LOGITS
    nos
    0.06
     Αν
    0.06
    нив
    0.06
    rough
    0.06
    atural
    0.06
    KP
    0.06
    сты
    0.06
    status
    0.06
     окра
    0.06
    正常
    0.06
    Act Density 0.007%

    No Known Activations