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

    Neuronpedia

    INDEX
    Explanations

    hurricanes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slight
    -0.09
    	switch
    -0.08
     türl
    -0.07
    ဈ
    -0.07
     CIS
    -0.07
    不知不
    -0.07
     tartış
    -0.07
    <TSource
    -0.06
    沨
    -0.06
    门外
    -0.06
    POSITIVE LOGITS
    _US
    0.07
    roduced
    0.07
    (reg
    0.07
    𝙈
    0.07
     <<"
    0.07
     postponed
    0.07
     ESA
    0.07
    (done
    0.07
    中式
    0.06
    玥
    0.06
    Act Density 0.003%

    No Known Activations