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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //////////////////////////////////////////////////////////////////////
    -0.06
    咨询
    -0.06
     refine
    -0.06
    Events
    -0.06
    Annotations
    -0.06
     vui
    -0.06
     Geneva
    -0.06
     karma
    -0.06
    認
    -0.06
    ForeignKey
    -0.06
    POSITIVE LOGITS
     adjusts
    0.07
     discharged
    0.07
    oscopic
    0.07
    riel
    0.07
    (heap
    0.07
     їй
    0.07
    vent
    0.06
     emphasized
    0.06
     adjusting
    0.06
     болезни
    0.06
    Act Density 0.044%

    No Known Activations