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

    Neuronpedia

    INDEX
    Explanations

    radio stations

    np_max-act · gemini-2.0-flash

    The neuron activates on radio station call signs (e.g. two‐ or four‐letter uppercase identifiers like “WFCL,” “WLQM-FM,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Above
    -0.08
    arehouse
    -0.07
    12
    -0.07
    15
    -0.07
    360
    -0.07
    heels
    -0.07
    HEEL
    -0.07
     achievable
    -0.07
    üns
    -0.07
     Prix
    -0.06
    POSITIVE LOGITS
     WF
    0.10
     Wilson
    0.09
     Wit
    0.09
     Walton
    0.09
    WI
    0.09
     WI
    0.08
    Wilson
    0.08
     Walter
    0.08
     WTF
    0.08
    wig
    0.08
    Act Density 0.382%

    No Known Activations