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

    Neuronpedia

    INDEX
    Explanations

    DNA extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Motorcycle
    -0.07
    _Con
    -0.06
    ์↵↵
    -0.06
     inserting
    -0.06
     paths
    -0.06
    购
    -0.06
     DEST
    -0.06
    دار
    -0.06
     intervention
    -0.06
    Paths
    -0.06
    POSITIVE LOGITS
    cial
    0.07
    promo
    0.07
    §
    0.07
    атег
    0.07
     hilarious
    0.07
     hầu
    0.06
     cmp
    0.06
    /task
    0.06
    sort
    0.06
    StateMachine
    0.06
    Act Density 0.053%

    No Known Activations