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

    Neuronpedia

    INDEX
    Explanations

    explain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kem
    -0.07
    位
    -0.07
     hunger
    -0.07
     поход
    -0.07
    腕
    -0.07
    資
    -0.07
    Made
    -0.07
     shoe
    -0.06
    502
    -0.06
     دان
    -0.06
    POSITIVE LOGITS
    'field
    0.07
    ARIANT
    0.06
     integrate
    0.06
    chrift
    0.06
    (default
    0.06
    naire
    0.06
     benz
    0.06
     JsonRequestBehavior
    0.06
    ůst
    0.06
    MQ
    0.06
    Act Density 0.019%

    No Known Activations