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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >w
    -0.07
    },
↵
    -0.06
    between
    -0.06
     pressure
    -0.06
     primeira
    -0.06
     ap
    -0.06
    .Bunifu
    -0.06
    ึง
    -0.06
    Between
    -0.06
     Paras
    -0.06
    POSITIVE LOGITS
     Lomb
    0.07
     превыш
    0.06
    tiler
    0.06
    .Dao
    0.06
    _leg
    0.06
    getRequest
    0.06
     detay
    0.06
     repertoire
    0.06
     Embed
    0.06
     toll
    0.06
    Act Density 0.020%

    No Known Activations