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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and logical relationships

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

    Comes before "and" or similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    if and only if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.92
    ScopeManager
    -0.84
    BeginContext
    -0.72
     queſta
    -0.65
    UnsafeEnabled
    -0.64
    DockStyle
    -0.63
    :✨
    -0.61
     resourceCulture
    -0.61
    CloseOperation
    -0.60
    principalColumn
    -0.59
    POSITIVE LOGITS
     and
    0.94
    且
    0.75
    并且
    0.62
     và
    0.60
    and
    0.60
     And
    0.58
     but
    0.57
    AndSet
    0.56
    และ
    0.53
    かつ
    0.53
    Act Density 0.963%

    No Known Activations