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

    Neuronpedia

    INDEX
    Explanations

    shortness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glad
    -0.07
     pessim
    -0.06
     Newly
    -0.06
     proceeding
    -0.06
     collaborators
    -0.06
     mocks
    -0.06
     necessity
    -0.06
     Consequently
    -0.06
     plugs
    -0.06
     propri
    -0.06
    POSITIVE LOGITS
    .copyWith
    0.07
     bitwise
    0.07
    Ар
    0.07
    紹
    0.07
    (separator
    0.07
    (RuntimeObject
    0.07
     bulb
    0.06
    ستر
    0.06
     mar
    0.06
     هنگام
    0.06
    Act Density 0.021%

    No Known Activations