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
    떵
    -0.09
     يعتبر
    -0.07
    嵊
    -0.07
    ﮏ
    -0.07
    묄
    -0.07
    _startup
    -0.06
    来临
    -0.06
    zew
    -0.06
    这对于
    -0.06
    ,LOCATION
    -0.06
    POSITIVE LOGITS
     VLAN
    0.07
    |↵
    0.07
    芙蓉
    0.07
    powered
    0.07
    rape
    0.07
    围绕
    0.07
    >*
    0.07
    ربط
    0.07
     goddess
    0.07
     resolves
    0.07
    Act Density 0.003%

    No Known Activations