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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    respect
    -0.07
     historian
    -0.06
    Bits
    -0.06
    POR
    -0.06
    _invite
    -0.06
     Laws
    -0.06
     Κατηγορία
    -0.06
    poke
    -0.06
    GH
    -0.06
    ')";↵
    -0.06
    POSITIVE LOGITS
     aqui
    0.07
     consume
    0.07
     Newark
    0.06
     snapchat
    0.06
     algunas
    0.06
     doğal
    0.06
     getNext
    0.06
     genç
    0.06
    forma
    0.06
     обеспеч
    0.06
    Act Density 0.004%

    No Known Activations