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

    Neuronpedia

    INDEX
    Explanations

    numeric questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     positively
    -0.08
     cuộc
    -0.07
     этим
    -0.07
    植
    -0.06
     clinic
    -0.06
     Simply
    -0.06
     Odin
    -0.06
    _PHASE
    -0.06
     Orthodox
    -0.06
    /control
    -0.06
    POSITIVE LOGITS
     Vacc
    0.07
     количества
    0.07
     Alibaba
    0.06
    <tag
    0.06
    анная
    0.06
    _All
    0.06
    %%↵
    0.06
     Lottery
    0.06
    ระด
    0.06
     eventdata
    0.06
    Act Density 0.013%

    No Known Activations