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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron flags numeric or decimal‐formatted tokens (i.e. numbers and floats) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sanders
    -0.06
    >(↵
    -0.06
    [input
    -0.06
     migrants
    -0.06
    /issues
    -0.06
    _EDEFAULT
    -0.06
    typeName
    -0.06
     tether
    -0.06
    -outs
    -0.06
     konumu
    -0.06
    POSITIVE LOGITS
     With
    0.07
    万
    0.07
     Managed
    0.07
     EFF
    0.07
     with
    0.06
    �
    0.06
    ันธ
    0.06
     Ef
    0.06
     Pow
    0.06
    ledger
    0.06
    Act Density 0.051%

    No Known Activations