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

    Neuronpedia

    INDEX
    Explanations

    natural language text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stride
    -0.07
     Müdürlüğü
    -0.07
    σεις
    -0.07
    idine
    -0.06
    omez
    -0.06
     delic
    -0.06
    _SELECTED
    -0.06
     Legendary
    -0.06
    fect
    -0.06
     Stainless
    -0.06
    POSITIVE LOGITS
     stats
    0.06
    _ind
    0.06
    -save
    0.06
     photos
    0.06
    常
    0.06
     adverse
    0.06
     heap
    0.06
     arcade
    0.06
    -eye
    0.05
    _sep
    0.05
    Act Density 0.000%

    No Known Activations