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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lenght
    -0.06
     tabBar
    -0.06
     Webster
    -0.06
     appendString
    -0.06
    ecessary
    -0.06
    ickness
    -0.06
     folds
    -0.06
    _offer
    -0.06
     vog
    -0.06
     ตอน
    -0.06
    POSITIVE LOGITS
     //.
    0.07
    ле
    0.06
    .patient
    0.06
    ап
    0.06
     superstar
    0.06
    ?.
    0.06
    lamak
    0.06
     다운
    0.06
     Народ
    0.06
    urve
    0.06
    Act Density 0.012%

    No Known Activations