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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mallow
    -0.06
    lığını
    -0.06
    isinden
    -0.06
    ilton
    -0.06
    ेकर
    -0.06
    oled
    -0.06
    üt
    -0.06
    Ü
    -0.06
    Ђ
    -0.06
    >↵↵
    -0.06
    POSITIVE LOGITS
     راهنم
    0.07
     Rosa
    0.06
     aprove
    0.06
    porn
    0.06
     перв
    0.06
     aliqua
    0.06
     помощи
    0.06
     především
    0.06
    =YES
    0.06
    -directed
    0.06
    Act Density 0.051%

    No Known Activations