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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or state of being of the subject

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

    if you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.61
     <<<<<<<<<<<<<<
    -0.52
    TemporalType
    -0.51
    abestanden
    -0.50
    Xna
    -0.50
    tonsoft
    -0.48
     surla
    -0.47
    ScopeManager
    -0.47
     Roskov
    -0.46
     BoxFit
    -0.44
    POSITIVE LOGITS
     are
    0.53
    queles
    0.50
     Gläub
    0.46
     Berufung
    0.45
     Begleitung
    0.43
     Gegend
    0.43
     razonable
    0.41
     seragam
    0.41
     Räume
    0.41
     zainteres
    0.41
    Act Density 0.008%

    No Known Activations