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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وير
    -0.07
     ikea
    -0.07
     heal
    -0.07
    carry
    -0.07
    /fa
    -0.07
     पश
    -0.07
     merak
    -0.06
    .article
    -0.06
    ibe
    -0.06
    (PARAM
    -0.06
    POSITIVE LOGITS
     dokument
    0.07
    CLUDE
    0.07
    825
    0.06
    120
    0.06
    460
    0.06
    verify
    0.06
     Shed
    0.06
     pavement
    0.06
    Forms
    0.06
     Vintage
    0.06
    Act Density 0.000%

    No Known Activations