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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on dotted identifier sequences (object or template variable property names, e.g. “Lang.action.admin” or “Settings.adm_cache_clear_data”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     comp
    -0.07
     continuity
    -0.07
    .Merge
    -0.06
     STREAM
    -0.06
     जर
    -0.06
    	mouse
    -0.06
    nP
    -0.06
    _MIX
    -0.06
    .photos
    -0.06
     já
    -0.06
    POSITIVE LOGITS
    ̀
    0.06
    atility
    0.06
     Challenger
    0.06
    '))↵↵↵
    0.06
    ")(
    0.06
    alach
    0.06
     Morm
    0.06
    ACE
    0.06
     Indust
    0.06
    �
    0.06
    Act Density 0.006%

    No Known Activations