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

    Neuronpedia

    INDEX
    Explanations

    ri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     τρο
    -0.07
     infections
    -0.07
     Han
    -0.06
     гум
    -0.06
    utra
    -0.06
    angel
    -0.06
     Ger
    -0.06
    .masks
    -0.06
    .Free
    -0.06
    igel
    -0.06
    POSITIVE LOGITS
    JB
    0.07
    价
    0.07
    UNCT
    0.06
     ett
    0.06
     faithfully
    0.06
    OCUMENT
    0.06
     التص
    0.06
    TH
    0.06
    {}.
    0.06
    missive
    0.06
    Act Density 0.039%

    No Known Activations