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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">'↵
    -0.07
    ….↵↵
    -0.07
    -dismissible
    -0.07
    やって
    -0.07
    ippo
    -0.06
    -boot
    -0.06
    rollment
    -0.06
    America
    -0.06
    Om
    -0.06
    stoupil
    -0.06
    POSITIVE LOGITS
     reactions
    0.07
    ازی
    0.06
    =_('
    0.06
    ียม
    0.06
     Celebrity
    0.06
    弃
    0.06
     Lik
    0.06
    інь
    0.06
     ماند
    0.06
     okol
    0.06
    Act Density 0.486%

    No Known Activations