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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    屣
    -0.07
     eldre
    -0.07
    HEIGHT
    -0.07
     Mir
    -0.07
    Capacity
    -0.07
     delicate
    -0.07
    옂
    -0.07
    '.↵↵
    -0.07
    典雅
    -0.07
    垤
    -0.06
    POSITIVE LOGITS
     rog
    0.07
    sav
    0.07
     Thief
    0.07
    sal
    0.07
    lip
    0.07
    .Tile
    0.06
    arte
    0.06
     power
    0.06
    uje
    0.06
     Trav
    0.06
    Act Density 0.010%

    No Known Activations