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

    Neuronpedia

    INDEX
    Explanations

    subtraction equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    succ
    -0.07
    swap
    -0.06
     підс
    -0.06
     naw
    -0.06
     caval
    -0.06
    Clark
    -0.06
    motor
    -0.06
     ガ
    -0.06
     Yug
    -0.06
     δυ
    -0.06
    POSITIVE LOGITS
     pictures
    0.07
    alted
    0.07
    ै?↵
    0.07
    EEDED
    0.06
    생
    0.06
     occup
    0.06
    duct
    0.06
     utilise
    0.06
    olvable
    0.06
    ाव
    0.06
    Act Density 0.004%

    No Known Activations