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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     FH
    -0.07
    arrant
    -0.06
     içer
    -0.06
    erd
    -0.06
     Sender
    -0.06
    applicant
    -0.05
     Як
    -0.05
    ải
    -0.05
    uggest
    -0.05
    POSITIVE LOGITS
    (require
    0.07
    @Autowired
    0.06
    _answer
    0.06
    RectTransform
    0.06
    _HORIZONTAL
    0.06
    数据
    0.06
    StatusCode
    0.06
    (logits
    0.06
    تان
    0.06
    CALE
    0.06
    Act Density 0.119%

    No Known Activations