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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    39
    -0.07
    Coll
    -0.06
    ्टम
    -0.06
    раж
    -0.06
    ㅇ
    -0.06
     institutional
    -0.06
     лич
    -0.06
    DUCTION
    -0.06
    852
    -0.06
    .ob
    -0.06
    POSITIVE LOGITS
    kün
    0.07
    	to
    0.07
     scars
    0.07
    dhcp
    0.06
     неск
    0.06
    Cİ
    0.06
     observes
    0.06
    inue
    0.06
    庆
    0.06
     viet
    0.06
    Act Density 0.026%

    No Known Activations