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

    Neuronpedia

    INDEX
    Explanations

    certain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drawbacks
    -0.07
    ettle
    -0.07
     stri
    -0.07
    \Client
    -0.07
     JSImport
    -0.06
    224
    -0.06
     Colin
    -0.06
    یت
    -0.06
    ีเอ
    -0.06
    hei
    -0.06
    POSITIVE LOGITS
     Junction
    0.06
    GRA
    0.06
    Gr
    0.06
    ching
    0.06
    ','=',
    0.06
    stdlib
    0.06
     옷
    0.06
    __*/
    0.06
     Фран
    0.06
     ]
↵
    0.06
    Act Density 0.045%

    No Known Activations