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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onne
    -0.07
    .NonNull
    -0.06
    rado
    -0.06
    (emp
    -0.06
    ohen
    -0.06
     δο
    -0.06
     poisoned
    -0.06
    �
    -0.06
    ψε
    -0.06
     Yep
    -0.06
    POSITIVE LOGITS
    하지
    0.06
     SCE
    0.06
    接着
    0.06
    $form
    0.06
    \",↵
    0.06
     dumpster
    0.06
     enthusiast
    0.06
    Filter
    0.06
    ,arg
    0.06
     Service
    0.06
    Act Density 0.038%

    No Known Activations