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

    Neuronpedia

    INDEX
    Explanations

    formatting symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trfs
    -0.07
     zv
    -0.07
     зб
    -0.07
     hôm
    -0.07
    elen
    -0.06
     všechno
    -0.06
    ophobic
    -0.06
     utilization
    -0.06
    \Controllers
    -0.06
     butterflies
    -0.06
    POSITIVE LOGITS
    .wp
    0.07
    .land
    0.07
    #echo
    0.07
    =out
    0.06
    evento
    0.06
    ucursal
    0.06
    <typeof
    0.06
     contextual
    0.06
    /re
    0.06
    -basket
    0.06
    Act Density 0.002%

    No Known Activations