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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    層
    -0.07
    ToFile
    -0.07
    vine
    -0.07
     Kirst
    -0.06
     Jama
    -0.06
     consulting
    -0.06
    ":"/
    -0.06
     작업
    -0.06
     orchest
    -0.06
     altri
    -0.06
    POSITIVE LOGITS
     Terror
    0.07
    _agent
    0.07
     bikini
    0.07
    \Category
    0.06
    /<?
    0.06
    bean
    0.06
     Cameroon
    0.06
     wake
    0.06
    doll
    0.06
    assign
    0.06
    Act Density 0.207%

    No Known Activations