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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coconut
    -0.06
    UserInfo
    -0.06
    .LOC
    -0.06
     xn
    -0.06
    _wf
    -0.06
    infinity
    -0.06
     ambiance
    -0.06
     walnut
    -0.06
     algo
    -0.06
     Zone
    -0.06
    POSITIVE LOGITS
    Unable
    0.07
    겨
    0.07
    ollah
    0.06
    %"><
    0.06
    اعة
    0.06
     sobre
    0.06
    (times
    0.06
    هار
    0.06
    ระด
    0.06
    =forms
    0.06
    Act Density 0.008%

    No Known Activations