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

    Neuronpedia

    INDEX
    Explanations

    goal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atches
    -0.07
     array
    -0.07
    periments
    -0.07
     Trust
    -0.07
     transporting
    -0.07
    perience
    -0.07
     uniform
    -0.06
    things
    -0.06
     tract
    -0.06
    .uniform
    -0.06
    POSITIVE LOGITS
     goal
    0.11
     goals
    0.10
     Goal
    0.09
    -goal
    0.08
    goal
    0.08
    Goal
    0.08
    Goals
    0.08
     alcan
    0.07
    (goal
    0.07
    目标
    0.07
    Act Density 0.024%

    No Known Activations