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

    Neuronpedia

    INDEX
    Explanations

    teeth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ÑĢаÑģположен
    -0.28
    ноп
    -0.27
     sunrise
    -0.26
    oker
    -0.26
     Fig
    -0.26
    riad
    -0.26
    ÑĢен
    -0.25
    roids
    -0.25
    structor
    -0.24
    rule
    -0.24
    POSITIVE LOGITS
     plane
    0.28
    _subs
    0.27
    .setTag
    0.26
    åľ¨åħ¨åĽ½
    0.26
    çłĶ究æīĢ
    0.26
     cass
    0.25
    ást
    0.25
    ODB
    0.25
    /TR
    0.25
    oss
    0.24
    Act Density 3.228%

    No Known Activations