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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hq
    -0.08
     dici
    -0.07
    ublish
    -0.07
     chops
    -0.07
    xffff
    -0.07
    üyor
    -0.07
    𝗵
    -0.07
     Seasons
    -0.07
    脱发
    -0.07
     IMO
    -0.07
    POSITIVE LOGITS
     parchment
    0.07
    Led
    0.07
     hanno
    0.07
    匣
    0.07
    뾰
    0.07
    centroid
    0.07
    ┠
    0.07
    �
    0.07
    涟
    0.07
    ."','".$
    0.07
    Act Density 0.015%

    No Known Activations