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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PerPage
    -0.08
     HttpServlet
    -0.07
    №
    -0.06
    RequestMapping
    -0.06
    get
    -0.06
    SUMER
    -0.06
    送
    -0.06
     IDirect
    -0.06
    imps
    -0.06
    Builder
    -0.06
    POSITIVE LOGITS
     dahi
    0.07
    [arr
    0.07
    panic
    0.07
     Sasha
    0.06
     commentator
    0.06
     VAN
    0.06
     corresponds
    0.06
     mood
    0.06
     concerning
    0.06
    ]])↵
    0.06
    Act Density 0.000%

    No Known Activations