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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tik
    -0.07
    ...↵↵↵↵
    -0.07
    Timing
    -0.06
     execute
    -0.06
    °}
    -0.06
     بپ
    -0.06
    >↵↵↵↵↵
    -0.06
    memo
    -0.06
    +"</
    -0.06
    ｌ
    -0.06
    POSITIVE LOGITS
     sparkling
    0.07
    .gr
    0.06
    (boolean
    0.06
     jedin
    0.06
     يد
    0.06
    .cm
    0.06
    geois
    0.06
     кажд
    0.06
    ,label
    0.06
     этой
    0.06
    Act Density 0.173%

    No Known Activations