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
    ä½Ĩåį´
    -0.32
    ä½ĨæĪij们
    -0.32
    ä½Ĩåľ¨
    -0.26
    è·ŁæĪij说
    -0.26
    ä½Ĩä»ĸ们
    -0.25
    çļĦ身份
    -0.25
    suggest
    -0.25
    jourd
    -0.25
     but
    -0.25
    æ¶Ī失
    -0.25
    POSITIVE LOGITS
    å¼Ħ
    0.29
    ainty
    0.26
    ISM
    0.26
    ThanOr
    0.26
    icism
    0.25
     equip
    0.25
    aders
    0.25
    vanced
    0.25
    对æłĩ
    0.24
    éli
    0.24
    Act Density 0.014%

    No Known Activations