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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash

    The neuron detects the phrase “fall into” (as in “fall into this/that category”), signaling a classification or grouping expression.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vac
    -0.07
    _author
    -0.06
     beds
    -0.06
     Brothers
    -0.06
    зв
    -0.06
     CST
    -0.06
     布
    -0.06
     LSB
    -0.06
    z
    -0.06
     quality
    -0.06
    POSITIVE LOGITS
    .distance
    0.07
    oq
    0.07
    .removeAll
    0.07
     предпоч
    0.07
     �
    0.06
    oles
    0.06
     rests
    0.06
    	align
    0.06
     регулю
    0.06
     उस
    0.06
    Act Density 0.020%

    No Known Activations