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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ite
    -0.07
     Panthers
    -0.07
    若
    -0.07
     Efficiency
    -0.07
     integrate
    -0.07
     Cave
    -0.07
     ghetto
    -0.06
    :↵↵
    -0.06
    (norm
    -0.06
     sports
    -0.06
    POSITIVE LOGITS
    WSC
    0.07
     AngularFire
    0.07
     lượt
    0.06
     ww
    0.06
    zerbai
    0.06
     PLEASE
    0.06
     allerdings
    0.06
     kodu
    0.06
     게시물
    0.06
    ुगत
    0.06
    Act Density 0.012%

    No Known Activations