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

    Neuronpedia

    INDEX
    Explanations

    step

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nurturing
    -0.07
     nat
    -0.07
    Nu
    -0.07
    N
    -0.06
    Danger
    -0.06
    HING
    -0.06
     wow
    -0.06
     �
    -0.06
    sun
    -0.06
     ob
    -0.06
    POSITIVE LOGITS
    	import
    0.08
    系统
    0.07
    ~↵↵
    0.07
    	mod
    0.06
     dış
    0.06
     FG
    0.06
    _protocol
    0.06
    .apple
    0.06
    一起
    0.06
    (Post
    0.06
    Act Density 0.011%

    No Known Activations