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

    Neuronpedia

    INDEX
    Explanations

    numeric symbols and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    special characters and numbers interleaved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.69
    новништво
    -0.58
    RegressionTest
    -0.58
     betweenstory
    -0.54
     enfans
    -0.54
    ыгана
    -0.53
     οποίο
    -0.51
    RectangleBorder
    -0.50
    了嗎
    -0.50
     laikā
    -0.49
    POSITIVE LOGITS
    LOP
    0.46
     Sof
    0.46
     cp
    0.45
    %"),
    0.45
     Bab
    0.43
    Bab
    0.43
     chip
    0.42
    юй
    0.42
     TF
    0.42
    glDelete
    0.42
    Act Density 0.017%

    No Known Activations