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

    Neuronpedia

    INDEX
    Explanations

    poll results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     azi
    -0.07
     Towers
    -0.06
     від
    -0.06
    GROUP
    -0.06
     Fighters
    -0.06
    _COPY
    -0.06
     Middleware
    -0.06
     VStack
    -0.06
    _As
    -0.06
    營
    -0.06
    POSITIVE LOGITS
    根
    0.07
     inevitable
    0.06
    ised
    0.06
     Ess
    0.06
    FFE
    0.06
     ae
    0.06
     maxValue
    0.06
    almö
    0.06
    .n
    0.06
    �게
    0.06
    Act Density 0.008%

    No Known Activations