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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     руки
    -0.07
     obe
    -0.07
     hadde
    -0.06
    �
    -0.06
     ấm
    -0.06
    _outer
    -0.06
    otřeb
    -0.06
    ुपए
    -0.06
    Eigen
    -0.06
    eç
    -0.06
    POSITIVE LOGITS
    aleza
    0.07
     evolving
    0.06
     MEDIA
    0.06
     Marketing
    0.06
     Sark
    0.06
     Fetish
    0.06
     Kad
    0.06
    Ps
    0.06
     Hawaii
    0.06
     cst
    0.06
    Act Density 0.001%

    No Known Activations