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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    两个月
    -0.08
    漳州
    -0.08
     embarrassment
    -0.08
     vulnerable
    -0.08
     jobject
    -0.08
     pieniąd
    -0.08
    _variance
    -0.07
    濞
    -0.07
    倴
    -0.07
    Joe
    -0.07
    POSITIVE LOGITS
    iap
    0.08
    cki
    0.08
    ��
    0.06
    卡
    0.06
    -custom
    0.06
     יש
    0.06
     scr
    0.06
    igm
    0.06
     classrooms
    0.06
     appl
    0.06
    Act Density 0.098%

    No Known Activations