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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سین
    -0.07
    atório
    -0.07
    lowest
    -0.06
     ฿
    -0.06
    講
    -0.06
    少年
    -0.06
    oins
    -0.06
    たら
    -0.06
    ival
    -0.06
     emphasize
    -0.06
    POSITIVE LOGITS
     decrypted
    0.07
     Forms
    0.06
    :center
    0.06
     Dread
    0.06
     allergic
    0.06
    ереч
    0.06
    _cf
    0.06
     нату
    0.06
    .z
    0.06
    UFFER
    0.05
    Act Density 0.001%

    No Known Activations