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

    Neuronpedia

    INDEX
    Explanations

    I or you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棋
    -0.07
     दस
    -0.07
    .Atoi
    -0.07
     lonely
    -0.06
    -read
    -0.06
     Likely
    -0.06
    85
    -0.06
     џ
    -0.06
    17
    -0.06
     explanatory
    -0.06
    POSITIVE LOGITS
     Ticaret
    0.06
     Zac
    0.06
     skyline
    0.06
     Spa
    0.06
     �
    0.06
     Valerie
    0.06
    Sidebar
    0.06
     breakup
    0.06
    apid
    0.06
    оти
    0.06
    Act Density 0.023%

    No Known Activations