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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens representing floating‐point or decimal numeric values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     peninsula
    -0.06
     Hernandez
    -0.06
    eno
    -0.06
     pouch
    -0.05
    imating
    -0.05
     recognizes
    -0.05
     signing
    -0.05
     fold
    -0.05
     donation
    -0.05
    -short
    -0.05
    POSITIVE LOGITS
     é
    0.07
    طلق
    0.07
     stalk
    0.07
     assim
    0.07
    .isSuccessful
    0.06
    071
    0.06
     logits
    0.06
    している
    0.06
    coordinate
    0.06
    ailable
    0.06
    Act Density 0.169%

    No Known Activations