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

    Neuronpedia

    INDEX
    Explanations

    generated code

    np_max-act · gemini-2.0-flash

    The neuron detects terms from the Apache license’s warranty disclaimer section (e.g. “distributed,” “AS IS,” “WITHOUT WARRANTIES,” “limitations”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     effet
    -0.07
     Chad
    -0.07
     mũi
    -0.07
    _CLIP
    -0.07
     dra
    -0.07
     oğ
    -0.07
    (JS
    -0.06
     دخ
    -0.06
     Hoe
    -0.06
    (changes
    -0.06
    POSITIVE LOGITS
    _equals
    0.06
    Delayed
    0.06
    _picture
    0.06
    parent
    0.06
     LaTeX
    0.06
    ุล
    0.06
    	t
    0.06
    دة
    0.06
     restructuring
    0.06
    	ex
    0.06
    Act Density 0.005%

    No Known Activations