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

    Neuronpedia

    INDEX
    Explanations

    introducing lists after "including"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.51
    ’’
    0.51
     оба
    0.51
    و
    0.50
    )$
    0.49
     cú
    0.46
    ")
    0.45
    ôle
    0.45
    "),
    0.44
    ۔
    0.44
    POSITIVE LOGITS
    n
    0.64
    s
    0.56
    an
    0.56
     seedlings
    0.54
     sunsets
    0.53
    㚘
    0.52
     crustaceans
    0.52
    ма
    0.52
     organelles
    0.51
     almonds
    0.50
    Act Density 0.572%

    No Known Activations