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

    Neuronpedia

    INDEX
    Explanations

    A/B Testing and Surveys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ##
    -0.06
    in
    -0.06
     preca
    -0.06
     -,
    -0.06
     TI
    -0.06
    IODevice
    -0.06
     mgr
    -0.06
     Chuck
    -0.06
     Ti
    -0.06
    !--
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.17
    ÂĢÂĢ
    0.16
    ¦æĥħ
    0.14
    .Formatter
    0.12
    ¿ÃĤ
    0.12
    ******č\n
    0.12
    Âģ@
    0.12
    įng
    0.12
     -*-č\n
    0.12
    .Dictionary
    0.12
    Act Density 0.671%

    No Known Activations