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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming or structure definitions

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

    Russian and Scandinavian words and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    actylus
    -0.50
     billeder
    -0.48
    NOUNC
    -0.48
    🕝
    -0.47
    󠁢
    -0.47
    OnClickListener
    -0.46
     Bewußt
    -0.45
     kaarangay
    -0.45
     telefónica
    -0.45
    ACCIÓN
    -0.45
    POSITIVE LOGITS
     су
    1.60
    Су
    1.14
     Су
    1.12
    су
    0.94
     su
    0.70
     суд
    0.70
     Su
    0.68
     dry
    0.66
     суда
    0.64
    СУ
    0.60
    Act Density 0.000%

    No Known Activations