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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _weight
    -0.09
     Mit
    -0.08
     Weight
    -0.08
     Queen
    -0.07
     peso
    -0.07
     hool
    -0.07
     Maintaining
    -0.07
     addiction
    -0.07
     WH
    -0.07
     toxin
    -0.07
    POSITIVE LOGITS
    分别
    0.20
     각각
    0.16
     jeweils
    0.12
     respectively
    0.12
     birbir
    0.11
     separated
    0.11
    These
    0.11
     respectivos
    0.10
     respective
    0.10
     sépar
    0.10
    Act Density 0.102%

    No Known Activations