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

    Neuronpedia

    INDEX
    Explanations

    religion/spirituality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oppressed
    -0.07
    兹
    -0.07
    /tasks
    -0.07
    ouncy
    -0.06
    portlet
    -0.06
     FO
    -0.06
    -node
    -0.06
     empath
    -0.06
     brittle
    -0.06
     Carr
    -0.06
    POSITIVE LOGITS
    勇
    0.07
     receives
    0.07
     '-
    0.06
     saves
    0.06
    ste
    0.06
    .Te
    0.06
    .
↵
    0.06
    는데
    0.06
     PLAY
    0.06
     '$
    0.06
    Act Density 0.052%

    No Known Activations