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

    Neuronpedia

    INDEX
    Explanations

    flame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     software
    -0.08
    йт
    -0.07
     Γ
    -0.07
    .Operation
    -0.07
    Insp
    -0.07
    ardown
    -0.07
    multipart
    -0.06
    .phi
    -0.06
    โจ
    -0.06
    萩
    -0.06
    POSITIVE LOGITS
    ᤖ
    0.08
    Forgot
    0.07
    只是为了
    0.07
     presum
    0.07
    끓
    0.07
    时间为
    0.07
    ędzi
    0.07
    RES
    0.07
    ペン
    0.06
     Üniversites
    0.06
    Act Density 0.009%

    No Known Activations