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

    Neuronpedia

    INDEX
    Explanations

    Opinions, discussion

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    another
    -0.07
    (tensor
    -0.07
    -webpack
    -0.07
    珪
    -0.07
     mô
    -0.07
     entend
    -0.07
    亓
    -0.07
    Ek
    -0.07
     đảm
    -0.06
     än
    -0.06
    POSITIVE LOGITS
    澼
    0.07
    eliness
    0.07
    Issues
    0.07
    输送
    0.07
    毛病
    0.07
    BY
    0.06
    ='+
    0.06
     sincer
    0.06
    ывать
    0.06
     cartridges
    0.06
    Act Density 0.132%

    No Known Activations