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

    Neuronpedia

    INDEX
    Explanations

    mol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .patch
    -0.07
    	send
    -0.07
    荒
    -0.07
     �
    -0.07
    칭
    -0.06
     advance
    -0.06
    信息
    -0.06
     fascist
    -0.06
    شي
    -0.06
     ‎
    -0.06
    POSITIVE LOGITS
    礼仪
    0.08
    Ear
    0.07
    乐
    0.07
    وس
    0.07
    .NO
    0.07
    웩
    0.07
     Uruguay
    0.07
     wagon
    0.06
    Ӈ
    0.06
    MQ
    0.06
    Act Density 0.001%

    No Known Activations