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

    Neuronpedia

    INDEX
    Explanations

    hackathons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	builder
    -0.07
    .append
    -0.07
    �
    -0.07
    warz
    -0.06
     Derne
    -0.06
    小额贷款
    -0.06
    _spinner
    -0.06
    	wp
    -0.06
    (Language
    -0.06
    (SP
    -0.06
    POSITIVE LOGITS
    Definitions
    0.07
     tenía
    0.06
    公开发
    0.06
     qc
    0.06
    {|
    0.06
    南沙
    0.06
    军团
    0.06
     lowest
    0.06
     bots
    0.06
     CONSTANTS
    0.06
    Act Density 0.001%

    No Known Activations