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

    Neuronpedia

    INDEX
    Explanations

    references to community connections and personal stories

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

    always or fondly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.53
    elemField
    -0.52
    GEBURTSDATUM
    -0.51
    IntoConstraints
    -0.50
    AndroidJUnit
    -0.47
    jspb
    -0.46
     CreateTagHelper
    -0.46
     iterative
    -0.45
    fjspx
    -0.45
     незавершена
    -0.44
    POSITIVE LOGITS
     always
    0.62
     fondly
    0.59
    Always
    0.57
     Always
    0.56
     zawsze
    0.55
     altid
    0.55
     resourceCulture
    0.54
     alway
    0.54
    siempre
    0.54
     friendship
    0.54
    Act Density 0.016%

    No Known Activations