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

    Neuronpedia

    INDEX
    Explanations

    shot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mix
    -0.08
    Ny
    -0.07
     Chase
    -0.07
     retire
    -0.07
     sabotage
    -0.07
    的身体
    -0.07
    eil
    -0.07
    आ
    -0.07
    כס
    -0.07
    Tickets
    -0.07
    POSITIVE LOGITS
    itemid
    0.08
     dequeueReusableCellWithIdentifier
    0.07
    ')}}">↵
    0.07
    犷
    0.07
     damer
    0.07
     suger
    0.07
    虤
    0.07
     sockfd
    0.07
     presumed
    0.07
    一刀
    0.07
    Act Density 0.008%

    No Known Activations