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

    Neuronpedia

    INDEX
    Explanations

    cipher

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spinner
    -0.07
    (callback
    -0.07
    收费站
    -0.07
    引入
    -0.07
    atu
    -0.07
    ının
    -0.07
     deserve
    -0.07
    작
    -0.06
     biết
    -0.06
     trừ
    -0.06
    POSITIVE LOGITS
    $form
    0.06
     fertility
    0.06
    	host
    0.06
     Hao
    0.06
     Hosting
    0.06
    _IMETHOD
    0.06
    modity
    0.06
     billionaires
    0.06
    RIORITY
    0.06
     security
    0.06
    Act Density 0.010%

    No Known Activations