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

    Neuronpedia

    INDEX
    Explanations

    Future technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    簌
    -0.07
     xAxis
    -0.07
     לכם
    -0.07
    千方
    -0.07
     complaining
    -0.07
    olleyError
    -0.07
    밴
    -0.07
    -it
    -0.06
     Acting
    -0.06
     ENTER
    -0.06
    POSITIVE LOGITS
     ware
    0.08
     angered
    0.07
    ﻚ
    0.07
    短缺
    0.07
    🔍
    0.07
     room
    0.07
    friends
    0.07
    نو
    0.06
    .double
    0.06
     Time
    0.06
    Act Density 0.065%

    No Known Activations