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

    Neuronpedia

    INDEX
    Explanations

    questions about you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ¶Į
    -0.13
    .Formatter
    -0.12
    įng
    -0.10
    ĥ½
    -0.10
    ¬´
    -0.09
    ¦æĥħ
    -0.09
    ¨ë¶Ģ
    -0.09
    СÐŀ
    -0.09
     -*-č\n
    -0.09
    ıa
    -0.09
    POSITIVE LOGITS
     your
    0.11
     yourself
    0.11
    ä½łçļĦ
    0.10
    your
    0.09
    .scalablytyped
    0.09
    ?\n\n
    0.09
    ?\n
    0.09
     tpl
    0.08
     RN
    0.08
     Cah
    0.08
    Act Density 0.350%

    No Known Activations