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

    Neuronpedia

    INDEX
    Explanations

    Generating code

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     finalized
    -0.06
    钬
    -0.06
    鸷
    -0.06
    缜
    -0.06
    멓
    -0.06
     incontro
    -0.06
    蠖
    -0.06
    锝
    -0.06
    ȅ
    -0.06
    겇
    -0.06
    POSITIVE LOGITS
     elast
    0.08
    _print
    0.07
    .constraint
    0.07
     unexpected
    0.07
     초기
    0.07
    lam
    0.07
     jedem
    0.07
     diffusion
    0.07
    _loop
    0.07
    -shared
    0.07
    Act Density 0.233%

    No Known Activations