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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or questioning motives

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

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jsPsych
    -0.64
     autorytatywna
    -0.64
    posedge
    -0.60
     ujednoznacz
    -0.58
     Pingback
    -0.54
    ScopeManager
    -0.53
     iVar
    -0.53
     categoryId
    -0.53
    AnchorTagHelper
    -0.52
    listdir
    -0.52
    POSITIVE LOGITS
     pierna
    0.45
     paisagem
    0.44
     curiosidad
    0.43
     kiin
    0.43
     cubierto
    0.42
     arcilla
    0.41
     jaula
    0.41
     botellas
    0.41
     atmósfera
    0.40
     fría
    0.40
    Act Density 0.017%

    No Known Activations