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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     системы
    -0.07
     por
    -0.06
    .Hour
    -0.06
    myp
    -0.06
     minimum
    -0.06
    进入
    -0.06
     adap
    -0.06
    ്
    -0.06
    ズ
    -0.06
    :]↵
    -0.06
    POSITIVE LOGITS
    )&&
    0.07
     Canucks
    0.06
     LAP
    0.06
     sluggish
    0.06
     Mathematic
    0.06
     defin
    0.06
    _IE
    0.06
    áře
    0.06
     menn
    0.06
    _HEAP
    0.06
    Act Density 0.048%

    No Known Activations