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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruta
    -0.06
    ANDLE
    -0.06
    owler
    -0.06
     racer
    -0.06
     easing
    -0.06
    _topic
    -0.06
    参
    -0.06
    auce
    -0.06
    ESİ
    -0.06
    xae
    -0.06
    POSITIVE LOGITS
    На
    0.07
    Opens
    0.07
    Ð
    0.07
     переп
    0.07
     Hunger
    0.06
    Within
    0.06
    0.06
     educate
    0.06
    .erb
    0.06
    CTSTR
    0.06
    Act Density 0.144%

    No Known Activations