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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Definitions
    -0.07
     характ
    -0.06
     VH
    -0.06
     geliyor
    -0.06
    ethereum
    -0.06
     bày
    -0.06
    _DSP
    -0.06
    §ظ
    -0.06
    _io
    -0.06
     عندما
    -0.06
    POSITIVE LOGITS
     KH
    0.08
     العربية
    0.07
     Serum
    0.07
    登录
    0.07
     Στα
    0.07
     Andersen
    0.07
    :'
    0.07
     Sơn
    0.06
     mattresses
    0.06
    ,:]
    0.06
    Act Density 0.028%

    No Known Activations