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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ure
    -0.07
    硼
    -0.07
    �
    -0.07
     forc
    -0.07
     SELF
    -0.07
     functionalities
    -0.07
    (ierr
    -0.07
    _prec
    -0.07
     stealth
    -0.07
    hz
    -0.07
    POSITIVE LOGITS
    踞
    0.07
    שפע
    0.07
     changing
    0.07
    可以说
    0.06
    峡谷
    0.06
    座
    0.06
     tabela
    0.06
    솨
    0.06
    writing
    0.06
    CLI
    0.06
    Act Density 0.008%

    No Known Activations