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

    Neuronpedia

    INDEX
    Explanations

    degree amount

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rightful
    -0.08
     datings
    -0.07
    🏃
    -0.07
     accomp
    -0.07
     JsonResult
    -0.07
    .AR
    -0.07
     sécur
    -0.07
    (console
    -0.07
    Als
    -0.07
    otor
    -0.07
    POSITIVE LOGITS
     işlem
    0.08
    stores
    0.07
    Set
    0.07
    前任
    0.07
     +
    0.07
    iff
    0.07
     stub
    0.06
     أكبر
    0.06
    묽
    0.06
    わかって
    0.06
    Act Density 0.043%

    No Known Activations