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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts, particularly denominators and positive/negative numbers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    év
    -0.06
     only
    -0.06
    938
    -0.06
    ihu
    -0.06
    addElement
    -0.06
    åıªæľī
    -0.06
    remen
    -0.06
     csak
    -0.06
    mium
    -0.05
    aku
    -0.05
    POSITIVE LOGITS
    Depending
    0.07
     depending
    0.07
     Depending
    0.07
    ếp
    0.06
    ãĤ¸
    0.06
    Ø´ÙĪ
    0.06
     varying
    0.06
     ÎłÏģÏī
    0.06
     '{@
    0.06
     διά
    0.06
    Act Density 0.344%

    No Known Activations