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

    Neuronpedia

    INDEX
    Explanations

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Shaft
    -0.07
     adapted
    -0.06
     Anyway
    -0.06
     ابتدا
    -0.06
    urst
    -0.06
    urator
    -0.06
     Remarks
    -0.06
     said
    -0.06
    ！”↵↵
    -0.06
    POSITIVE LOGITS
    getMessage
    0.07
    <message
    0.07
     keyPressed
    0.07
    �i
    0.06
    (ast
    0.06
     Rogue
    0.06
    上传
    0.06
     で
    0.06
     типа
    0.06
    нист
    0.06
    Act Density 0.026%

    No Known Activations