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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    媒
    -0.07
     avid
    -0.07
    =''↵
    -0.06
    袋
    -0.06
    された
    -0.06
     شوند
    -0.06
     arsenal
    -0.06
    裡
    -0.06
    $/
    -0.06
    /day
    -0.06
    POSITIVE LOGITS
     omit
    0.07
     ceux
    0.07
     candidates
    0.06
    loha
    0.06
    ');?>↵
    0.06
    ände
    0.06
    getDb
    0.06
    lte
    0.06
     erect
    0.06
    ammad
    0.06
    Act Density 0.168%

    No Known Activations