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

    Neuronpedia

    INDEX
    Explanations

    divided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tales
    -0.07
     penetrated
    -0.07
    CELER
    -0.07
     socially
    -0.07
     addresses
    -0.06
     increasingly
    -0.06
     STUD
    -0.06
    まま
    -0.06
    광고
    -0.06
     marketing
    -0.06
    POSITIVE LOGITS
    	ep
    0.06
    	of
    0.06
     guint
    0.06
    nums
    0.06
     hn
    0.06
     yapacak
    0.05
     vod
    0.05
    Framebuffer
    0.05
     HF
    0.05
    _VOICE
    0.05
    Act Density 0.016%

    No Known Activations