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

    Neuronpedia

    INDEX
    Explanations

    itol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .e
    -0.07
     Blu
    -0.07
     tasting
    -0.07
    �
    -0.07
     Gods
    -0.07
    wit
    -0.06
     xls
    -0.06
    -lang
    -0.06
     E
    -0.06
    mage
    -0.06
    POSITIVE LOGITS
     доказ
    0.07
    ,.
    0.06
     contro
    0.06
    LANGADM
    0.06
    +l
    0.06
    σιμοποι
    0.06
     मजब
    0.06
    ."""↵↵
    0.06
     incorporates
    0.06
    _invoice
    0.06
    Act Density 0.001%

    No Known Activations