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

    Neuronpedia

    INDEX
    Explanations

    insertions/modifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zek
    -0.08
    -summary
    -0.07
     argparse
    -0.07
     sond
    -0.06
     uh
    -0.06
    )size
    -0.06
    PropertyDescriptor
    -0.06
    üstü
    -0.06
     Bernie
    -0.06
    eteria
    -0.06
    POSITIVE LOGITS
    Amount
    0.07
     Offering
    0.07
     بسی
    0.07
    accepted
    0.06
     ami
    0.06
    �
    0.06
     joven
    0.06
    춘
    0.06
    さんは
    0.06
    IDI
    0.06
    Act Density 0.002%

    No Known Activations