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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of specific vector or force “components” (e.g. axial, horizontal, radial, vertical, arc-direction components) in technical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    '
↵
↵
    -0.07
    reece
    -0.07
    連
    -0.06
    utschen
    -0.06
    okud
    -0.06
     іде
    -0.06
    У
    -0.06
    '↵↵
    -0.06
    λευτα
    -0.06
    CustomerId
    -0.06
    POSITIVE LOGITS
    PRE
    0.07
    =current
    0.07
     slož
    0.07
     вида
    0.06
     concrete
    0.06
    Strong
    0.06
    INC
    0.06
    -length
    0.06
     Delegate
    0.06
     voiture
    0.06
    Act Density 0.007%

    No Known Activations