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

    Neuronpedia

    INDEX
    Explanations

    Debugging or repeated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .INTEGER
    -0.08
    $num
    -0.06
     multiplying
    -0.06
     Entities
    -0.06
     prm
    -0.06
    _sess
    -0.06
     rem
    -0.06
     probl
    -0.06
    $p
    -0.06
    .Serializer
    -0.06
    POSITIVE LOGITS
     expended
    0.07
     　　　　　　　　　　　　
    0.06
    �
    0.06
    орош
    0.06
     daily
    0.06
     sustained
    0.06
    ']
↵
    0.06
     contamin
    0.06
    itably
    0.06
    ilent
    0.06
    Act Density 0.002%

    No Known Activations