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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     обол
    -0.07
     Will
    -0.07
     있을
    -0.06
    乾
    -0.06
    TING
    -0.06
     Ging
    -0.06
     Mou
    -0.06
    (blocks
    -0.06
     astronauts
    -0.06
    POSITIVE LOGITS
     deal
    0.07
    真正
    0.06
    xhr
    0.06
     NSMutableArray
    0.06
     sosyal
    0.06
     المهنة
    0.06
     перев
    0.06
     irrigation
    0.06
    ěn
    0.06
    ']="
    0.06
    Act Density 0.000%

    No Known Activations