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

    Neuronpedia

    INDEX
    Explanations

    Place Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sample
    -0.07
     mujer
    -0.06
     tunnel
    -0.06
     cycle
    -0.06
    pline
    -0.06
     killer
    -0.06
     spy
    -0.06
    -S
    -0.06
     espionage
    -0.06
     Sequence
    -0.06
    POSITIVE LOGITS
    ‌اند
    0.07
     디자인
    0.07
     incurred
    0.07
    .pem
    0.06
    戶
    0.06
    -таки
    0.06
    �
    0.06
     králov
    0.06
     Zwe
    0.06
     centerY
    0.06
    Act Density 0.012%

    No Known Activations