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

    Neuronpedia

    INDEX
    Explanations

    Plotlines/summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tisk
    -0.07
     gid
    -0.06
    Ki
    -0.06
     CSI
    -0.06
    _pins
    -0.06
     dictate
    -0.06
    essions
    -0.06
    Driven
    -0.06
    ihar
    -0.06
     Publish
    -0.06
    POSITIVE LOGITS
     renov
    0.07
    ertino
    0.06
     chị
    0.06
     Elf
    0.06
    (vp
    0.06
    eways
    0.06
    .walk
    0.06
    營
    0.06
     pir
    0.06
    スポ
    0.06
    Act Density 0.008%

    No Known Activations