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

    Neuronpedia

    INDEX
    Explanations

    Code imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Damen
    -0.07
    itable
    -0.07
    _hop
    -0.07
     Philip
    -0.06
    不过是
    -0.06
     değerlendirme
    -0.06
     Heather
    -0.06
     unfair
    -0.06
    엪
    -0.06
    成熟的
    -0.06
    POSITIVE LOGITS
     base
    0.08
                            
↵
    0.08
    視
    0.07
    aggio
    0.07
    $view
    0.07
    >>();↵
    0.07
    天
    0.07
     SignIn
    0.07
    ga
    0.07
    ')}}">
    0.07
    Act Density 0.029%

    No Known Activations