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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hậu
    -0.07
     機
    -0.07
     Parliamentary
    -0.06
    iad
    -0.06
     tires
    -0.06
     capabilities
    -0.06
     回
    -0.06
    样
    -0.06
     build
    -0.06
     eventual
    -0.06
    POSITIVE LOGITS
    ftar
    0.06
     conta
    0.06
    보험
    0.06
    [rand
    0.06
    ibNameOrNil
    0.06
    .addObserver
    0.06
    sanitize
    0.06
     brutality
    0.06
     blowjob
    0.06
     chi
    0.06
    Act Density 0.004%

    No Known Activations