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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating physical movement or displacement away from a location

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

    away from or out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.45
    ISupport
    -0.45
     surla
    -0.44
    AppRoutingModule
    -0.43
    bkz
    -0.42
    ⓧ
    -0.41
     GreatSchools
    -0.40
     exper
    -0.40
     softwares
    -0.39
    Hentet
    -0.39
    POSITIVE LOGITS
     nevoie
    0.43
     liderança
    0.42
    away
    0.42
    ivably
    0.41
     noDo
    0.41
     retain
    0.41
     представление
    0.40
    ndes
    0.40
     retaining
    0.40
     weg
    0.40
    Act Density 0.050%

    No Known Activations