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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     authors
    -0.07
     ум
    -0.07
     узн
    -0.07
    zv
    -0.07
     WCS
    -0.06
    .condition
    -0.06
    STOP
    -0.06
     IB
    -0.06
    DOC
    -0.06
    istické
    -0.06
    POSITIVE LOGITS
    登場
    0.07
     Sew
    0.06
    OTOS
    0.06
    ictured
    0.06
    驚
    0.06
     Early
    0.06
     آنان
    0.06
     Mastery
    0.06
     REG
    0.06
    Seriously
    0.06
    Act Density 0.012%

    No Known Activations