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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INLINE
    -0.07
     –
    -0.06
     lashes
    -0.06
    ({'
    -0.06
    -low
    -0.06
    (msg
    -0.06
    SGlobal
    -0.06
    秀
    -0.06
    احث
    -0.06
    -ground
    -0.06
    POSITIVE LOGITS
     služ
    0.07
    екту
    0.07
    _don
    0.07
     />
    0.07
     teknik
    0.06
    #w
    0.06
     devast
    0.06
    bose
    0.06
    �
    0.06
    科技
    0.06
    Act Density 0.186%

    No Known Activations