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

    Neuronpedia

    INDEX
    Explanations

    code structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ugly
    -0.07
    TOTAL
    -0.06
     bekannt
    -0.06
     cage
    -0.06
     bleak
    -0.06
    reetings
    -0.06
    dling
    -0.06
     Discuss
    -0.06
    _BINDING
    -0.06
    овано
    -0.06
    POSITIVE LOGITS
    ูตร
    0.07
    	Title
    0.07
    　r
    0.07
     Druh
    0.06
    .or
    0.06
    ainting
    0.06
     overlay
    0.06
    .EX
    0.06
    �
    0.06
     qualifiers
    0.06
    Act Density 0.008%

    No Known Activations