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

    Neuronpedia

    INDEX
    Explanations

    detect

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     nei
    -0.07
     hey
    -0.07
    .peer
    -0.07
    igious
    -0.07
    isks
    -0.07
    ༽
    -0.07
    keep
    -0.07
     scars
    -0.07
    刊
    -0.07
    _experience
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Rad
    0.07
     влия
    0.07
    三分之一
    0.07
     slave
    0.07
     وز
    0.07
     factual
    0.07
    нстру
    0.07
    的程度
    0.07
    起重机
    0.06
    Act Density 0.036%

    No Known Activations