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

    Neuronpedia

    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tree
    -0.07
    _digit
    -0.06
    slashes
    -0.06
    legal
    -0.06
    tones
    -0.06
     Truly
    -0.06
    gorm
    -0.06
    ttl
    -0.06
    DOCUMENT
    -0.06
     rencontres
    -0.06
    POSITIVE LOGITS
     weave
    0.08
     点
    0.07
     weaving
    0.07
     unravel
    0.07
     нам
    0.07
     thread
    0.07
     konci
    0.06
     inevitable
    0.06
     single
    0.06
    钢
    0.06
    Act Density 0.044%

    No Known Activations