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

    Neuronpedia

    INDEX
    Explanations

    say "our"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있으며
    -0.06
    lož
    -0.06
    니스
    -0.06
     Christians
    -0.06
    )+'
    -0.06
    Restart
    -0.06
     networks
    -0.06
     trình
    -0.06
     runner
    -0.06
     nouvel
    -0.06
    POSITIVE LOGITS
    ProgressBar
    0.06
     cười
    0.06
     schwar
    0.06
    Da
    0.06
     OPC
    0.06
    prof
    0.06
    είς
    0.06
     replen
    0.06
     Published
    0.06
    unlock
    0.06
    Act Density 0.071%

    No Known Activations