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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultural
    -0.07
     Jenn
    -0.06
     Located
    -0.06
    .assertIn
    -0.06
     marrying
    -0.06
     наиболее
    -0.06
     Aust
    -0.06
    최고
    -0.06
    methodPointerType
    -0.06
    )})
    -0.06
    POSITIVE LOGITS
     flam
    0.07
     псих
    0.06
     acne
    0.06
    _tokenize
    0.06
     aimed
    0.06
    asks
    0.06
    атку
    0.06
    speed
    0.06
     زیست
    0.06
    Gift
    0.06
    Act Density 0.074%

    No Known Activations