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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics and performance metrics

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

    Number words after prepositions

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.82
     Several
    -0.76
     Two
    -0.75
    XtraBars
    -0.74
    Several
    -0.74
     MainAxisSize
    -0.71
     Few
    -0.69
     ३
    -0.66
    Two
    -0.66
    RectangleBorder
    -0.66
    POSITIVE LOGITS
     eight
    0.56
     zero
    0.56
     eig
    0.56
     f
    0.54
     five
    0.54
     thee
    0.54
     nine
    0.54
     si
    0.54
     fi
    0.53
     seven
    0.52
    Act Density 0.320%

    No Known Activations