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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash

    It activates on floating‐point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    song
    -0.07
    İn
    -0.06
    oin
    -0.06
    OX
    -0.06
     Paleo
    -0.06
    �
    -0.06
    _mgmt
    -0.06
    cba
    -0.06
    ์ว
    -0.06
     Retrieve
    -0.06
    POSITIVE LOGITS
     Background
    0.06
     banking
    0.06
    _lengths
    0.06
     Sl
    0.06
     pict
    0.06
    .DB
    0.06
     чис
    0.06
     "";↵
    0.06
     бет
    0.06
    segments
    0.06
    Act Density 0.016%

    No Known Activations