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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating essential recommendations or must-see items

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

    following "must."

    np_acts-logits-general · gemini-2.0-flash

    must watch or read

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.78
    MemoryWarning
    -0.69
    AutoScaleMode
    -0.67
     AssemblyProduct
    -0.65
    SourceChecksum
    -0.65
    ArrowToggle
    -0.65
    ServletConfig
    -0.64
    titleMargin
    -0.62
    InstrumentedTest
    -0.62
    mybatisplus
    -0.62
    POSITIVE LOGITS
     MUST
    1.11
     must
    1.10
    must
    1.06
     Must
    1.02
    Must
    1.01
     unbedingt
    1.00
    MUST
    0.94
     worth
    0.91
     wajib
    0.90
     definitely
    0.90
    Act Density 0.109%

    No Known Activations