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

    Neuronpedia

    INDEX
    Explanations

    character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _box
    -0.07
     RX
    -0.07
    �
    -0.06
    ummy
    -0.06
    _undo
    -0.06
     دهند
    -0.06
    �
    -0.06
     práce
    -0.06
    ef
    -0.06
     quer
    -0.06
    POSITIVE LOGITS
    文献
    0.07
     Else
    0.07
    -heavy
    0.07
     MediaType
    0.07
    ]},↵
    0.06
    ander
    0.06
     fscanf
    0.06
    ellery
    0.06
    veillance
    0.06
    United
    0.06
    Act Density 0.014%

    No Known Activations