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
     lidi
    -0.07
     Conrad
    -0.07
    etas
    -0.07
    Close
    -0.07
     Horde
    -0.06
     paciente
    -0.06
    pipes
    -0.06
     ce
    -0.06
     Sem
    -0.06
     ple
    -0.06
    POSITIVE LOGITS
    	of
    0.07
    (ml
    0.07
    .good
    0.06
    >>>>>>>>
    0.06
     تی
    0.06
     flipping
    0.06
     ชนะ
    0.06
    рал
    0.06
    already
    0.06
    717
    0.06
    Act Density 0.000%

    No Known Activations