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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всех
    -0.07
    adm
    -0.07
    238
    -0.06
    -overlay
    -0.06
    ds
    -0.06
    leur
    -0.06
     trừ
    -0.06
    bitrary
    -0.06
    '-
    -0.06
    +f
    -0.06
    POSITIVE LOGITS
     contacting
    0.07
     Eston
    0.07
     بشر
    0.06
     γρα
    0.06
    (any
    0.06
     facto
    0.06
     wasted
    0.06
     worked
    0.06
    marshaller
    0.06
    .Direction
    0.06
    Act Density 0.003%

    No Known Activations