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

    Neuronpedia

    INDEX
    Explanations

    extend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    261
    -0.07
    293
    -0.07
     Lab
    -0.07
    巴
    -0.07
    463
    -0.07
     Beach
    -0.06
    Rock
    -0.06
     about
    -0.06
    _proba
    -0.06
    แพ
    -0.06
    POSITIVE LOGITS
     extended
    0.12
     extension
    0.12
     extending
    0.12
     extensions
    0.12
    extension
    0.11
     Extension
    0.11
     extend
    0.11
    extended
    0.10
     Extend
    0.10
    Extension
    0.10
    Act Density 0.025%

    No Known Activations