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

    Neuronpedia

    INDEX
    Explanations

    effecting change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MapPath
    -0.07
     whatsapp
    -0.07
    考试
    -0.06
     capital
    -0.06
     pitchers
    -0.06
    48
    -0.06
    ору
    -0.06
    	Dictionary
    -0.06
    币
    -0.06
    计划
    -0.06
    POSITIVE LOGITS
     Andr
    0.07
    _REFER
    0.07
    earer
    0.07
    WX
    0.06
     WX
    0.06
    toc
    0.06
    ,len
    0.06
    _MON
    0.06
    ause
    0.06
    geme
    0.06
    Act Density 0.096%

    No Known Activations