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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     반드시
    -0.08
     hasta
    -0.07
     получения
    -0.07
     reduce
    -0.07
     dispositivo
    -0.07
    慮
    -0.07
    דווח
    -0.07
    致使
    -0.07
     conosc
    -0.07
    ﲪ
    -0.07
    POSITIVE LOGITS
     LONG
    0.06
    不良
    0.06
    _Price
    0.06
     în
    0.06
    EX
    0.06
     Goals
    0.06
    Changes
    0.06
    Funny
    0.06
     �
    0.06
     bucks
    0.06
    Act Density 0.045%

    No Known Activations