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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¡
    -0.07
     █
    -0.07
     vacancy
    -0.07
     sensation
    -0.06
    -list
    -0.06
    Vy
    -0.06
     וג
    -0.06
     hộ
    -0.06
     vic
    -0.06
    内の
    -0.06
    POSITIVE LOGITS
    ROT
    0.07
    TECTION
    0.07
    𫞩
    0.07
     USED
    0.07
    靓丽
    0.07
     comfortably
    0.06
     seriously
    0.06
    健康的
    0.06
    _serv
    0.06
    OOT
    0.06
    Act Density 0.010%

    No Known Activations