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

    Neuronpedia

    INDEX
    Explanations

    quotation punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FIELDS
    -0.07
     fragmentation
    -0.07
    ‑
    -0.06
     شاه
    -0.06
     fragmented
    -0.06
     Pune
    -0.06
     fj
    -0.06
    ーカー
    -0.06
    anton
    -0.06
    agen
    -0.06
    POSITIVE LOGITS
     于
    0.07
    Архів
    0.07
     mission
    0.06
     Hash
    0.06
     recommand
    0.06
    یشن
    0.06
     CSI
    0.06
     Beet
    0.06
    SSH
    0.06
    ffffffff
    0.06
    Act Density 0.002%

    No Known Activations