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

    Neuronpedia

    INDEX
    Explanations

    staffing and wording

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cmb
    -0.07
    149
    -0.06
     invites
    -0.06
    cheduler
    -0.06
    =W
    -0.06
    接受
    -0.06
     fright
    -0.06
    baru
    -0.06
     rectangles
    -0.06
     نحوه
    -0.06
    POSITIVE LOGITS
     ranked
    0.07
     leveled
    0.07
     plated
    0.07
     lining
    0.07
     timed
    0.06
    -hearted
    0.06
    ็ด
    0.06
    Motion
    0.06
     lined
    0.06
     priced
    0.06
    Act Density 0.185%

    No Known Activations