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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and discussions regarding expectations and agreements

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

    people think they would

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     min
    -0.40
     Min
    -0.36
     TEXT
    -0.34
     pes
    -0.33
     Text
    -0.32
    беріга
    -0.32
     Officer
    -0.32
     Schreib
    -0.32
     scissors
    -0.32
     minimo
    -0.32
    POSITIVE LOGITS
     ब्रेकडाउन
    0.83
    rungsseite
    0.72
    LookAnd
    0.66
    ValueStyle
    0.64
    ArrowToggle
    0.62
     saurait
    0.62
     AssemblyCompany
    0.61
    səhifə
    0.60
    AsUp
    0.59
    はじめに
    0.59
    Act Density 0.043%

    No Known Activations