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

    Neuronpedia

    INDEX
    Explanations

    counting digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Funk
    -0.09
     Tot
    -0.08
     doorway
    -0.08
     concentrates
    -0.08
     estimates
    -0.08
     Weed
    -0.08
     geeignet
    -0.08
     obedience
    -0.08
     rents
    -0.07
     canon
    -0.07
    POSITIVE LOGITS
    _digit
    0.10
    digits
    0.09
    Number
    0.09
    Digit
    0.09
    Digits
    0.09
    digit
    0.08
    _digits
    0.08
    -digit
    0.08
     digits
    0.08
    ATS
    0.08
    Act Density 0.020%

    No Known Activations