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

    Neuronpedia

    INDEX
    Explanations

    printing/logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expressions
    -0.07
    .YEAR
    -0.06
     sơ
    -0.06
     восп
    -0.06
    blockquote
    -0.06
     الآن
    -0.06
    PostExecute
    -0.06
     относ
    -0.06
     homework
    -0.06
    ึก
    -0.06
    POSITIVE LOGITS
    .Or
    0.08
     Queensland
    0.07
     STR
    0.07
    利
    0.07
     effectiveness
    0.07
     STREET
    0.07
    geist
    0.07
    ROOM
    0.06
     nominate
    0.06
     CUR
    0.06
    Act Density 0.028%

    No Known Activations