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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    66
    -0.06
    kontakte
    -0.06
     ft
    -0.06
     homeowners
    -0.06
     Dame
    -0.06
     imap
    -0.06
     metric
    -0.06
     浙江
    -0.06
     Я
    -0.06
     throat
    -0.06
    POSITIVE LOGITS
    _UNS
    0.07
     msgid
    0.07
    _ADV
    0.07
     nouvelles
    0.07
     (?)
    0.07
    สาม
    0.07
    紧
    0.07
     incentiv
    0.07
    parentId
    0.06
     stationed
    0.06
    Act Density 0.028%

    No Known Activations