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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pově
    -0.06
     assaulting
    -0.06
    總
    -0.06
     международ
    -0.06
     quốc
    -0.06
     ıs
    -0.06
     Argentine
    -0.05
    meni
    -0.05
    Disposed
    -0.05
     reservation
    -0.05
    POSITIVE LOGITS
    (topic
    0.07
     environments
    0.07
    >,↵
    0.07
     تأ
    0.07
     intric
    0.07
    ppard
    0.06
    >>,
    0.06
     incorporating
    0.06
    .Stop
    0.06
    _STS
    0.06
    Act Density 0.000%

    No Known Activations