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

    Neuronpedia

    INDEX
    Explanations

    Calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .libs
    -0.06
    ynchronized
    -0.06
    Aws
    -0.06
     wget
    -0.06
     filtering
    -0.06
    指
    -0.06
    _rw
    -0.06
    Ctl
    -0.06
     Sid
    -0.06
     Wasser
    -0.06
    POSITIVE LOGITS
    thes
    0.07
     raising
    0.07
    (Component
    0.07
    izi
    0.07
    ]'↵
    0.06
     sophistication
    0.06
     alle
    0.06
    ;
↵
    0.06
    nahme
    0.06
     Booking
    0.06
    Act Density 0.010%

    No Known Activations