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

    Neuronpedia

    INDEX
    Explanations

    handling requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stocked
    0.51
    ارك
    0.51
     prevalence
    0.47
     angles
    0.47
     affidavit
    0.47
     histoires
    0.46
     scriptures
    0.46
     forested
    0.46
     integrals
    0.46
     copyrights
    0.46
    POSITIVE LOGITS
    for
    0.49
    TECHN
    0.46
    Packaging
    0.45
    儘
    0.45
    LEVEL
    0.44
    Transport
    0.44
    exclusive
    0.44
    maras
    0.42
    *$
    0.42
    UES
    0.41
    Act Density 0.005%

    No Known Activations