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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens containing digits (e.g. version numbers or numeric identifiers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     noss
    -0.07
     closeButton
    -0.06
    mts
    -0.06
     brave
    -0.06
    Berlin
    -0.06
    ť
    -0.06
    \Security
    -0.06
    Disk
    -0.06
     Conte
    -0.06
    .acc
    -0.06
    POSITIVE LOGITS
    ecycle
    0.07
     saúde
    0.06
    ('|
    0.06
     relocation
    0.06
     механіз
    0.06
    ”，
    0.06
    het
    0.06
     многих
    0.06
     describing
    0.06
     gob
    0.06
    Act Density 0.000%

    No Known Activations