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

    Neuronpedia

    INDEX
    Explanations

    Limits and numbers

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens specifying a length or size constraint (e.g. “maximum 3 words”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Vari
    -0.07
    ุ่
    -0.06
    >{
    -0.06
    лені
    -0.06
    quality
    -0.06
    	var
    -0.05
    unication
    -0.05
     synchronization
    -0.05
    vb
    -0.05
     AST
    -0.05
    POSITIVE LOGITS
    essaging
    0.08
     excer
    0.07
     roy
    0.07
    .setX
    0.07
     Asking
    0.07
     rencontrer
    0.07
     Bonds
    0.07
     sayı
    0.07
    ]|[
    0.07
    ってい
    0.06
    Act Density 0.001%

    No Known Activations