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

    Neuronpedia

    INDEX
    Explanations

    Formatting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     visitors
    -0.07
     SL
    -0.07
     DAN
    -0.07
    まった
    -0.06
    农业
    -0.06
     ASA
    -0.06
     `${
    -0.06
     CBS
    -0.06
     Zahl
    -0.06
     forEach
    -0.06
    POSITIVE LOGITS
     bog
    0.06
    >B
    0.06
     використ
    0.06
    刻
    0.06
    .abspath
    0.06
    『
    0.06
     ￣
    0.06
    发出
    0.06
     emph
    0.06
     birçok
    0.06
    Act Density 0.025%

    No Known Activations