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

    Neuronpedia

    INDEX
    Explanations

    the concept of taking a break or recovering

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

    rest assured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acri
    -0.58
     coaxial
    -0.56
    VersionUID
    -0.56
     Talon
    -0.55
    Galer
    -0.54
     iPhones
    -0.53
     punter
    -0.53
     conni
    -0.53
     Zola
    -0.52
     Maury
    -0.52
    POSITIVE LOGITS
     rest
    1.82
     Rest
    1.64
    rest
    1.63
    Rest
    1.60
     rested
    1.37
     REST
    1.33
    REST
    1.31
     rests
    1.27
     resting
    1.18
    rests
    1.05
    Act Density 0.012%

    No Known Activations