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

    Neuronpedia

    INDEX
    Explanations

    Words ending in al/ional/icional/eral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بودند
    -0.07
     furry
    -0.07
     العم
    -0.07
     jednu
    -0.06
     plusieurs
    -0.06
          ↵↵
    -0.06
     quatre
    -0.06
    备注
    -0.06
     varias
    -0.06
     earliest
    -0.06
    POSITIVE LOGITS
     tying
    0.08
    (find
    0.07
     pil
    0.07
     identity
    0.07
    gradable
    0.06
     сказ
    0.06
    BTC
    0.06
    uses
    0.06
     controlling
    0.06
    IMATION
    0.06
    Act Density 0.141%

    No Known Activations