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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stringWith
    -0.06
    North
    -0.06
    ِ
    -0.06
    ::*
    -0.06
    Viol
    -0.06
    Ｒ
    -0.06
    ео
    -0.06
     crews
    -0.06
     tiếp
    -0.06
    条
    -0.06
    POSITIVE LOGITS
    mentioned
    0.07
     dealloc
    0.07
    #+#+
    0.07
    届
    0.07
    ana
    0.07
     ap
    0.07
    ุส
    0.06
     служ
    0.06
     Hispan
    0.06
    ecast
    0.06
    Act Density 0.012%

    No Known Activations