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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endl
    -0.08
    ingo
    -0.07
    IMATE
    -0.07
    urch
    -0.06
    яем
    -0.06
    	v
    -0.06
    ži
    -0.06
    ouro
    -0.06
    "in
    -0.06
     O
    -0.06
    POSITIVE LOGITS
     isi
    0.06
     офици
    0.06
     rộng
    0.06
    REPORT
    0.06
    стри
    0.06
    .dirname
    0.06
    518
    0.06
    _limit
    0.06
     الکتر
    0.06
    兒
    0.06
    Act Density 0.009%

    No Known Activations