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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hol
    -0.06
    ospel
    -0.06
     valido
    -0.06
    ependency
    -0.06
     Annual
    -0.06
     uncommon
    -0.06
     Leban
    -0.06
     hug
    -0.06
     Strings
    -0.06
    Bal
    -0.06
    POSITIVE LOGITS
    >')
    0.07
     undermines
    0.07
    輸
    0.07
     参数
    0.07
     astronomical
    0.06
     humiliation
    0.06
    APON
    0.06
    _REPO
    0.06
    按
    0.06
    ￣
    0.06
    Act Density 0.019%

    No Known Activations