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

    Neuronpedia

    INDEX
    Explanations

    restaurant reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    墓
    -0.07
     Communities
    -0.06
     attacks
    -0.06
    _mot
    -0.06
    ंगठन
    -0.06
    shade
    -0.06
    aded
    -0.06
     Negro
    -0.06
     vertically
    -0.06
     Expression
    -0.06
    POSITIVE LOGITS
     duplic
    0.08
    Wie
    0.07
     &'
    0.07
    승
    0.06
     слух
    0.06
     Chin
    0.06
    uplic
    0.06
    =df
    0.06
     أب
    0.06
     fits
    0.06
    Act Density 0.036%

    No Known Activations