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

    Neuronpedia

    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash

    This neuron responds to en‐dash constructions indicating compass direction spans (e.g. “east–west” or “north–south”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FORMAT
    -0.06
    θρω
    -0.06
     pubs
    -0.06
    .sid
    -0.06
     Iter
    -0.06
     ""},↵
    -0.06
     Kale
    -0.06
     ale
    -0.06
     وك
    -0.06
     ض
    -0.06
    POSITIVE LOGITS
    –
    0.08
    ･
    0.07
    accom
    0.07
    –
    0.07
    ()\
    0.07
    pm
    0.07
     ako
    0.06
    _sf
    0.06
    しても
    0.06
    conduct
    0.06
    Act Density 0.010%

    No Known Activations