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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and operations

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

    Mathematical formulas with multiplication and addition

    np_acts-logits-general · gemini-2.0-flash

    numbers and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.72
     sandero
    -0.53
    ouac
    -0.52
    ⟬
    -0.52
    ImageContext
    -0.52
     archae
    -0.51
     faſt
    -0.51
    PlayerPrefs
    -0.50
    ఔ
    -0.50
    ьаж
    -0.49
    POSITIVE LOGITS
    addGroup
    0.55
     Ch
    0.54
     "..\..\..\
    0.52
    RegistryLite
    0.52
     por
    0.52
    small
    0.52
     Su
    0.51
     negligible
    0.51
    berian
    0.50
    DebuggerNonUser
    0.49
    Act Density 0.732%

    No Known Activations