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

    Neuronpedia

    INDEX
    Explanations

    respectively

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gorithm
    -0.08
     submitted
    -0.07
     handling
    -0.07
     Uno
    -0.07
     Cav
    -0.07
     Woods
    -0.07
     основ
    -0.06
     gear
    -0.06
     center
    -0.06
    Ord
    -0.06
    POSITIVE LOGITS
     respectively
    0.07
    .Project
    0.07
     vra
    0.07
     niece
    0.07
    \Exceptions
    0.06
    .per
    0.06
     cousin
    0.06
    ruta
    0.06
    requests
    0.06
    рования
    0.06
    Act Density 0.011%

    No Known Activations