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

    Neuronpedia

    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å½»
    -0.29
    theast
    -0.28
    aten
    -0.28
    ein
    -0.26
    #↵↵
    -0.26
    _append
    -0.25
    Web
    -0.24
    ĮĢ
    -0.24
    combe
    -0.24
    ueue
    -0.24
    POSITIVE LOGITS
     individual
    0.38
     apparently
    0.30
     despite
    0.30
     none
    0.29
    尽管
    0.28
     although
    0.28
    individual
    0.28
     there
    0.28
     even
    0.27
    /how
    0.27
    Act Density 0.013%

    No Known Activations