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

    Neuronpedia

    INDEX
    Explanations

    terms related to escape and migration

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

    Movement or transfer, often involving "into"

    np_acts-logits-general · gemini-2.0-flash

    movement and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.63
    ScopeManager
    -0.52
    olella
    -0.48
    InjectAttribute
    -0.47
    znego
    -0.47
    culable
    -0.46
    iläum
    -0.46
     îi
    -0.46
     AssemblyCulture
    -0.45
    eradish
    -0.45
    POSITIVE LOGITS
     into
    2.18
     naar
    1.73
     INTO
    1.72
     onto
    1.71
    into
    1.70
    Into
    1.68
     Into
    1.66
     hacia
    1.64
     toward
    1.55
     towards
    1.55
    Act Density 0.675%

    No Known Activations