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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tamb
    -0.07
     whale
    -0.06
    robots
    -0.06
    654
    -0.06
     Cameras
    -0.06
     Crystal
    -0.06
     fame
    -0.06
     shitty
    -0.06
     Benghazi
    -0.06
     ışık
    -0.06
    POSITIVE LOGITS
    .nano
    0.07
    —even
    0.07
     negotiated
    0.06
    ,proto
    0.06
    Sizes
    0.06
     Article
    0.06
     thousand
    0.06
    Backing
    0.06
     tighten
    0.06
    [string
    0.06
    Act Density 0.017%

    No Known Activations