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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stakeholder
    -0.09
    表达
    -0.08
     валют
    -0.08
     stakeholders
    -0.08
    列表
    -0.08
     lexer
    -0.08
     글로벌
    -0.08
     जीत
    -0.08
     unanimously
    -0.08
    数
    -0.08
    POSITIVE LOGITS
     cylindrical
    0.16
     Cylinder
    0.13
     цилинд
    0.13
     cylinder
    0.13
    -shaped
    0.12
    -cylinder
    0.12
     cylinders
    0.11
     hollow
    0.11
     nozzle
    0.11
     cilind
    0.11
    Act Density 0.037%

    No Known Activations