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

    Neuronpedia

    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on standalone numeric tokens—especially floating-point decimals used in rule or citation references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     recreated
    -0.07
    	ps
    -0.06
     Combined
    -0.06
    473
    -0.06
    атели
    -0.06
     ragazzi
    -0.06
    	k
    -0.06
     Kardash
    -0.06
     fick
    -0.06
     hashCode
    -0.06
    POSITIVE LOGITS
    \Client
    0.07
     clubhouse
    0.07
     tonnes
    0.07
    blocks
    0.07
    (Build
    0.06
     orgy
    0.06
     حکوم
    0.06
     griev
    0.06
     Call
    0.06
    -host
    0.06
    Act Density 0.014%

    No Known Activations