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

    Neuronpedia

    INDEX
    Explanations

    list of items/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     b
    -0.42
     cu
    -0.42
     star
    -0.42
     e
    -0.41
     
    -0.41
     “
    -0.40
     "
    -0.40
     c
    -0.39
     p
    -0.39
     sub
    -0.38
    POSITIVE LOGITS
    1.05
    mybatisplus
    0.90
     démocr
    0.88
     élas
    0.87
     <=",
    0.86
     itſelf
    0.83
     Monfieur
    0.83
     themſelves
    0.82
     myſelf
    0.82
    Geplaatst
    0.82
    Act Density 0.001%

    No Known Activations