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

    Neuronpedia

    INDEX
    Explanations

    ogram

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cls
    -0.07
    ませ
    -0.06
    瓤
    -0.06
     preschool
    -0.06
    삑
    -0.06
     Servlet
    -0.06
    停放
    -0.06
    瘆
    -0.06
    /music
    -0.06
    玉石
    -0.06
    POSITIVE LOGITS
    人大
    0.07
    不服
    0.07
     HK
    0.07
     /*<<<
    0.07
    ataires
    0.06
    外媒
    0.06
     keyboard
    0.06
     leer
    0.06
     semi
    0.06
     rumours
    0.06
    Act Density 0.006%

    No Known Activations