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

    Neuronpedia

    INDEX
    Explanations

    ONS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Generator
    -0.07
    Eval
    -0.06
    omit
    -0.06
     High
    -0.06
    Coordinator
    -0.06
    換
    -0.06
    allocate
    -0.06
     clean
    -0.06
     neden
    -0.06
     hanging
    -0.06
    POSITIVE LOGITS
    ős
    0.08
     rahatsız
    0.08
     المس
    0.07
    TJ
    0.07
     yo
    0.07
    س
    0.06
    (fb
    0.06
    ß
    0.06
    .DoesNotExist
    0.06
    inos
    0.06
    Act Density 0.019%

    No Known Activations