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

    Neuronpedia

    INDEX
    Explanations

    EA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pigeon
    -0.07
     pow
    -0.07
    ầy
    -0.06
    \Catalog
    -0.06
    ormap
    -0.06
     hva
    -0.06
     �
    -0.06
    \Bridge
    -0.06
    .lucene
    -0.06
    \Message
    -0.06
    POSITIVE LOGITS
     процед
    0.07
     Gam
    0.07
     fries
    0.06
     driv
    0.06
    _THAN
    0.06
    θ
    0.06
     onun
    0.06
    Phi
    0.06
     Immutable
    0.06
    PER
    0.06
    Act Density 0.007%

    No Known Activations