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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,text
    -0.08
     feelings
    -0.08
     tentative
    -0.07
     damages
    -0.07
    }");
↵
    -0.07
    不知不觉
    -0.07
    ifetime
    -0.07
     kost
    -0.07
     gest
    -0.07
    ativity
    -0.06
    POSITIVE LOGITS
    锜
    0.08
    揳
    0.07
    測
    0.07
     ioctl
    0.07
    igne
    0.07
    _CRYPTO
    0.07
    ᴙ
    0.07
    oure
    0.07
    筀
    0.07
    iro
    0.07
    Act Density 0.000%

    No Known Activations