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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numberWith
    -0.07
    _OPER
    -0.07
    SocketAddress
    -0.06
     пот
    -0.06
    _neurons
    -0.06
    director
    -0.06
    Aud
    -0.06
     Siz
    -0.06
    !=
    -0.06
     sunrise
    -0.06
    POSITIVE LOGITS
     Emblem
    0.06
     velvet
    0.06
     cif
    0.06
    _HARD
    0.06
    _hi
    0.06
    =create
    0.06
    706
    0.06
    sm
    0.06
    oned
    0.06
     Excellent
    0.06
    Act Density 0.013%

    No Known Activations