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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :↵
    -0.07
    :
↵
    -0.07
     село
    -0.07
     nationals
    -0.06
    าะ
    -0.06
    :↵↵
    -0.06
    @hotmail
    -0.06
     corridors
    -0.06
    '.↵↵
    -0.06
    ariance
    -0.06
    POSITIVE LOGITS
    emann
    0.07
     subroutine
    0.07
     lái
    0.07
     몸
    0.06
    (Common
    0.06
     Coron
    0.06
     Decode
    0.06
    uento
    0.06
     Besch
    0.06
    281
    0.06
    Act Density 0.061%

    No Known Activations