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

    Neuronpedia

    INDEX
    Explanations

    xy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Breast
    -0.07
    atoi
    -0.07
    aire
    -0.06
     bí
    -0.06
    =z
    -0.06
     卡
    -0.06
    IRE
    -0.06
     tấm
    -0.06
     zahl
    -0.06
    /job
    -0.06
    POSITIVE LOGITS
    lemma
    0.08
    mentation
    0.07
     upset
    0.07
    HexString
    0.07
     graduate
    0.06
     intimacy
    0.06
    napshot
    0.06
     fraudulent
    0.06
     groundwater
    0.06
     VARIABLES
    0.06
    Act Density 0.005%

    No Known Activations