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

    Neuronpedia

    INDEX
    Explanations

    technology forums

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Under
    -0.08
    (where
    -0.07
    .mac
    -0.07
    (av
    -0.07
     зар
    -0.07
    Jun
    -0.07
    Ton
    -0.07
    ]';↵
    -0.06
    未经
    -0.06
     age
    -0.06
    POSITIVE LOGITS
    ฬ
    0.07
     hurdle
    0.07
    -core
    0.07
    든
    0.07
     robotics
    0.07
     hurdles
    0.07
    mods
    0.07
     worries
    0.07
    制定了
    0.07
    /read
    0.07
    Act Density 0.092%

    No Known Activations