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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pounding
    -0.07
    getConfig
    -0.07
     cellar
    -0.07
    fusion
    -0.07
     allergic
    -0.06
    Po
    -0.06
    greso
    -0.06
     Proper
    -0.06
    وزيع
    -0.06
     punching
    -0.06
    POSITIVE LOGITS
    xCF
    0.06
     WHO
    0.06
     hopes
    0.06
     catastrophe
    0.06
    ++++++++++++++++
    0.06
     rem
    0.06
     Я
    0.06
    cripts
    0.06
    .SelectCommand
    0.06
    司
    0.06
    Act Density 0.018%

    No Known Activations