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

    Neuronpedia

    INDEX
    Explanations

    radi

    np_max-act · gemini-2.0-flash

    The neuron detects the character sequence “radi” (as in radiology, radiomics, radiodensity) within words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     kHz
    -0.07
     Zoo
    -0.07
     Poker
    -0.07
     Gn
    -0.06
    ektor
    -0.06
    -neck
    -0.06
    .UNRELATED
    -0.06
     Chapel
    -0.06
    Too
    -0.06
    Hint
    -0.06
    POSITIVE LOGITS
     radi
    0.12
     Radi
    0.11
    Radi
    0.11
     Rad
    0.10
    .radius
    0.08
     Telerik
    0.08
     ради
    0.08
     rad
    0.08
    adi
    0.08
    ADI
    0.08
    Act Density 0.009%

    No Known Activations