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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .false
    -0.07
    э
    -0.07
    Christian
    -0.07
    Bruce
    -0.07
    Salt
    -0.07
     Ridge
    -0.07
     deform
    -0.07
     uomini
    -0.06
     fasting
    -0.06
     precondition
    -0.06
    POSITIVE LOGITS
     FT
    0.06
    ılı
    0.06
     되
    0.06
    uppy
    0.06
    .Chrome
    0.06
    _JS
    0.06
    �
    0.05
    Detach
    0.05
    ایان
    0.05
    sortBy
    0.05
    Act Density 0.019%

    No Known Activations