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

    Neuronpedia

    INDEX
    Explanations

    persists

    np_max-act · gemini-2.0-flash

    This neuron identifies numeric tokens representing floating‐point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    雅
    -0.06
     comforts
    -0.06
    CCC
    -0.06
     serviced
    -0.06
    ازه
    -0.06
     عصر
    -0.06
    �
    -0.06
    /function
    -0.06
    Hub
    -0.06
     Pháp
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ])):↵
    0.07
    ->{'
    0.06
     concl
    0.06
    ське
    0.06
     ­
    0.06
     kunnen
    0.06
    ("-
    0.06
    ('-
    0.06
    .pyplot
    0.06
    Act Density 0.352%

    No Known Activations