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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lund
    -0.07
     Brady
    -0.06
    (actual
    -0.06
     Peng
    -0.06
     exterior
    -0.06
    liche
    -0.06
    >NN
    -0.06
    antry
    -0.06
    ۲۸
    -0.06
     connector
    -0.06
    POSITIVE LOGITS
    ूचन
    0.08
    (bit
    0.07
    :message
    0.07
     저장
    0.07
     focal
    0.07
    -messages
    0.06
     rising
    0.06
    ikip
    0.06
     tipping
    0.06
    기가
    0.06
    Act Density 0.018%

    No Known Activations