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

    Neuronpedia

    INDEX
    Explanations

    numerical data and related operations

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

    Numerical counts or indices

    np_acts-logits-general · gemini-2.0-flash

    counts or parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.20
     témoig
    -1.18
     ſei
    -1.14
     beſte
    -1.13
     MainAxisSize
    -1.12
     zwiſchen
    -1.12
    migrationBuilder
    -1.10
    <unused52>
    -1.09
    <unused16>
    -1.09
    <unused8>
    -1.09
    POSITIVE LOGITS
    3
    0.40
    7
    0.40
    2
    0.39
    4
    0.39
    5
    0.39
    0
    0.37
    1
    0.36
    6
    0.35
    8
    0.35
    9
    0.34
    Act Density 1.227%

    No Known Activations