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

    Neuronpedia

    INDEX
    Explanations

    IA

    np_max-act · gemini-2.0-flash

    This neuron consistently activates on the two‐letter token "IA," i.e. the substring “ia” often appearing as the ending of words (e.g. “Columbia”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ait
    -0.07
     Jahres
    -0.06
     Janet
    -0.06
    โรงแรม
    -0.06
     throwError
    -0.06
     xn
    -0.06
     beware
    -0.06
     zk
    -0.06
    แม
    -0.06
    Sur
    -0.06
    POSITIVE LOGITS
     subdivisions
    0.08
     storage
    0.08
    λα
    0.07
     overcrow
    0.07
    avatars
    0.07
    ivos
    0.07
     hose
    0.07
    λά
    0.06
     fragments
    0.06
    ادم
    0.06
    Act Density 0.000%

    No Known Activations