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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wooden
    -0.07
    σκευ
    -0.06
    .ast
    -0.06
     Coins
    -0.06
    ('.')
    -0.06
     Galactic
    -0.06
     Increment
    -0.06
    юдж
    -0.06
    スト
    -0.06
     difficult
    -0.06
    POSITIVE LOGITS
     shin
    0.09
     toh
    0.06
    бря
    0.06
     Newfoundland
    0.06
     h�
    0.06
     vowels
    0.06
    AY
    0.06
     torino
    0.06
    Move
    0.05
    foundland
    0.05
    Act Density 0.020%

    No Known Activations