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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tear
    -0.07
    ..."↵
    -0.06
     mainBundle
    -0.06
     restore
    -0.06
     Meet
    -0.06
     barred
    -0.06
    },"
    -0.06
    Â
    -0.06
    归纳
    -0.06
    ㅡ
    -0.06
    POSITIVE LOGITS
     Einsatz
    0.08
    一对一
    0.07
    igmat
    0.07
    其次是
    0.07
     хозяй
    0.07
     agon
    0.07
    .PrimaryKey
    0.07
     púb
    0.07
    开口
    0.07
    演技
    0.07
    Act Density 0.000%

    No Known Activations