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

    Neuronpedia

    INDEX
    Explanations

    qu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _data
    -0.08
     está
    -0.07
    (Attribute
    -0.07
     cancer
    -0.07
    _payload
    -0.07
    _INDEX
    -0.07
     eyel
    -0.07
    唱
    -0.07
     planes
    -0.07
    icle
    -0.07
    POSITIVE LOGITS
    uations
    0.06
    -aware
    0.06
    арх
    0.06
    /')↵
    0.06
    never
    0.05
     ATF
    0.05
    .goBack
    0.05
    تی
    0.05
     Decor
    0.05
    grave
    0.05
    Act Density 0.005%

    No Known Activations