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

    Neuronpedia

    INDEX
    Explanations

    legal matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grape
    -0.07
    )))
    -0.07
    .recipe
    -0.07
     cried
    -0.07
    ))),
    -0.06
     ว
    -0.06
    ');
    -0.06
    >O
    -0.06
    -gr
    -0.06
    )")
    -0.06
    POSITIVE LOGITS
    DECL
    0.07
     Round
    0.06
    (docs
    0.06
     panic
    0.06
     sift
    0.06
     đổi
    0.06
     SetProperty
    0.06
     round
    0.06
     GURL
    0.06
    reject
    0.06
    Act Density 0.039%

    No Known Activations