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

    Neuronpedia

    INDEX
    Explanations

    performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fly
    -0.07
     Shaman
    -0.07
     Bent
    -0.06
    	me
    -0.06
    उन
    -0.06
    .ElementAt
    -0.06
     liar
    -0.06
     برج
    -0.06
    gte
    -0.06
    _MATERIAL
    -0.06
    POSITIVE LOGITS
    íc
    0.07
     Used
    0.07
     crim
    0.07
    ancock
    0.06
    Additional
    0.06
    startswith
    0.06
     init
    0.06
    引
    0.06
    ísticas
    0.06
    cxx
    0.06
    Act Density 0.028%

    No Known Activations