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

    Neuronpedia

    INDEX
    Explanations

    center

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -social
    -0.06
    IB
    -0.06
     vigor
    -0.06
    .Parcelable
    -0.06
    iphertext
    -0.06
     Saud
    -0.06
     insanity
    -0.06
    جات
    -0.06
    Open
    -0.06
     bounce
    -0.06
    POSITIVE LOGITS
    elerde
    0.06
     Script
    0.06
     assertFalse
    0.06
     Triumph
    0.06
     fizz
    0.06
     film
    0.06
     Disability
    0.06
     Directory
    0.06
    ulf
    0.06
    런
    0.06
    Act Density 0.002%

    No Known Activations