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

    Neuronpedia

    INDEX
    Explanations

    easiness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kil
    -0.07
     대
    -0.07
     Fay
    -0.06
     Wang
    -0.06
     Time
    -0.06
    ),$
    -0.06
    =False
    -0.06
     Survival
    -0.06
     Proud
    -0.06
    18
    -0.06
    POSITIVE LOGITS
    _OBJC
    0.06
     istiyorum
    0.06
     Moreover
    0.06
     ekran
    0.06
    (compare
    0.06
    nonatomic
    0.06
     glitter
    0.06
    Ố
    0.06
    。その
    0.06
    (connectionString
    0.06
    Act Density 0.033%

    No Known Activations