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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glamorous
    -0.08
    -webpack
    -0.07
    "M
    -0.07
     home
    -0.07
     het
    -0.06
    يلم
    -0.06
     HOME
    -0.06
    러스
    -0.06
     अश
    -0.06
     animals
    -0.06
    POSITIVE LOGITS
     eventName
    0.07
    ceu
    0.06
    asp
    0.06
     Antonio
    0.06
     Maintain
    0.06
    (flags
    0.06
     anak
    0.06
    launch
    0.06
    错误
    0.06
    panied
    0.06
    Act Density 0.009%

    No Known Activations