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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “RNN” (the recurrent neural network acronym) or closely related model references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uniqu
    -0.07
    .layouts
    -0.07
     sound
    -0.07
    488
    -0.06
    .Expressions
    -0.06
    537
    -0.06
    track
    -0.06
    �
    -0.06
    upid
    -0.06
    IID
    -0.06
    POSITIVE LOGITS
     woods
    0.07
     instrumental
    0.07
     substitution
    0.07
    _ste
    0.06
     fail
    0.06
     olds
    0.06
    าค
    0.06
     elapsedTime
    0.06
    	cin
    0.06
     severely
    0.06
    Act Density 0.179%

    No Known Activations