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

    Neuronpedia

    INDEX
    Explanations

    groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reopen
    -0.08
    .right
    -0.07
    SR
    -0.07
     expire
    -0.06
    xee
    -0.06
     serves
    -0.06
    疏散
    -0.06
    ienen
    -0.06
     moist
    -0.06
    视为
    -0.06
    POSITIVE LOGITS
     robe
    0.08
    넴
    0.06
    .Imp
    0.06
    珠
    0.06
     Apocalypse
    0.06
    רות
    0.06
     Quaternion
    0.06
     puede
    0.06
     Tales
    0.06
    .viewmodel
    0.06
    Act Density 0.055%

    No Known Activations