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

    Neuronpedia

    INDEX
    Explanations

    um

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PROJECT
    -0.07
    668
    -0.07
    698
    -0.07
    794
    -0.07
     pallet
    -0.06
     oznám
    -0.06
     إد
    -0.06
    Tasks
    -0.06
    ента
    -0.06
    724
    -0.06
    POSITIVE LOGITS
    jr
    0.07
    ος
    0.07
    レン
    0.07
    ]->
    0.07
     Few
    0.06
     치
    0.06
    indr
    0.06
    �체
    0.06
    avascript
    0.06
     Norman
    0.06
    Act Density 0.001%

    No Known Activations