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

    Neuronpedia

    INDEX
    Explanations

    receive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    玩具
    -0.09
    _photo
    -0.09
    
    -0.07
    pecies
    -0.07
     keyValue
    -0.07
    ziej
    -0.07
     attachments
    -0.07
    ходить
    -0.07
     labeled
    -0.07
     risky
    -0.07
    POSITIVE LOGITS
     declar
    0.07
    踊
    0.07
    赢得了
    0.07
    밌
    0.07
     Glück
    0.07
    stärke
    0.06
     Gilles
    0.06
    𥔲
    0.06
     célib
    0.06
    	glog
    0.06
    Act Density 0.223%

    No Known Activations