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

    Neuronpedia

    INDEX
    Explanations

    the/a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    510
    -0.07
     options
    -0.06
     "|
    -0.06
    -chain
    -0.06
     Cooke
    -0.06
     cocktail
    -0.06
     folders
    -0.06
     "'
    -0.06
    _circle
    -0.06
    "',
    -0.06
    POSITIVE LOGITS
     اتحاد
    0.07
    imed
    0.06
     funct
    0.06
    عود
    0.06
    �
    0.06
     послед
    0.06
     jan
    0.06
     alright
    0.06
     Genç
    0.06
    ША
    0.06
    Act Density 0.010%

    No Known Activations