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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on multi-word technology domain names—most prominently “Internet of Things” (and its IoT acronym).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     validations
    -0.08
    ¢
    -0.07
    _minimum
    -0.07
     chamber
    -0.06
     techniques
    -0.06
    ные
    -0.06
     Magazine
    -0.06
    _strength
    -0.06
     cu
    -0.06
    254
    -0.06
    POSITIVE LOGITS
     ↵	↵
    0.07
     eql
    0.06
     згод
    0.06
    'LBL
    0.06
     dreaded
    0.06
    Climate
    0.06
     rigged
    0.06
     бюдж
    0.06
     alex
    0.06
     ),
↵
    0.06
    Act Density 0.004%

    No Known Activations