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

    Neuronpedia

    INDEX
    Explanations

    WARRANTIES

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    のお
    -0.07
    dating
    -0.07
     magically
    -0.07
    姽
    -0.07
    �
    -0.07
    瑷
    -0.07
    想不到
    -0.07
    懒
    -0.07
    打败
    -0.06
     Ана
    -0.06
    POSITIVE LOGITS
     TM
    0.07
     mes
    0.07
     homosexuality
    0.07
    خفض
    0.07
    #Region
    0.07
    PackageName
    0.07
    ⊗
    0.07
     CID
    0.07
     varied
    0.07
    <source
    0.07
    Act Density 0.000%

    No Known Activations