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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Confirmed
    -0.07
    ίζ
    -0.07
     Treasury
    -0.07
     shades
    -0.07
    deş
    -0.07
    InputGroup
    -0.06
    ям
    -0.06
     جوان
    -0.06
    useRalative
    -0.06
    ุน
    -0.06
    POSITIVE LOGITS
     xong
    0.06
     Packs
    0.06
     Darwin
    0.06
    )(__
    0.06
     deduction
    0.06
     hizo
    0.06
     (__
    0.06
    _INFO
    0.06
    plays
    0.06
     Mahar
    0.06
    Act Density 0.036%

    No Known Activations