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

    Neuronpedia

    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     userdata
    -0.07
    서비스
    -0.06
     Alarm
    -0.06
    .jet
    -0.06
    jíž
    -0.06
     Hastings
    -0.06
    -за
    -0.06
     ducks
    -0.06
     yapar
    -0.06
    663
    -0.06
    POSITIVE LOGITS
    §
    0.07
     Strong
    0.07
    Moved
    0.07
     '
    0.07
     strong
    0.07
    …↵
    0.07
    -unstyled
    0.07
    (feature
    0.07
     styles
    0.06
    .X
    0.06
    Act Density 0.007%

    No Known Activations