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

    Neuronpedia

    INDEX
    Explanations

    however

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rat
    -0.06
    ыџN
    -0.06
     tung
    -0.05
    Dependencies
    -0.05
     тоб
    -0.05
    ادات
    -0.05
    steen
    -0.05
    ("{}
    -0.05
     '{}
    -0.05
     นาย
    -0.05
    POSITIVE LOGITS
     however
    0.11
     However
    0.09
    However
    0.07
    Moreover
    0.07
    ekkür
    0.07
    addEventListener
    0.07
     miners
    0.07
    however
    0.07
    nummer
    0.07
     kişisel
    0.07
    Act Density 0.038%

    No Known Activations