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

    Neuronpedia

    INDEX
    Explanations

    proper names, titles, and honorifics

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

    past tense verbs followed by "the" or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndFlush
    -0.41
    دانشنامهٔ
    -0.40
    Scénario
    -0.39
     adelant
    -0.38
    Parcelable
    -0.37
     Olímpicos
    -0.36
    Sucesor
    -0.36
     merci
    -0.35
    ENTITY
    -0.35
    esserung
    -0.35
    POSITIVE LOGITS
    rungsseite
    0.50
     transfieras
    0.50
    帖最后由
    0.48
    ":[{
    0.45
     الحره
    0.45
    tagPool
    0.44
     صوتيه
    0.43
     AssemblyProduct
    0.43
    SequentialGroup
    0.42
    pantalón
    0.42
    Act Density 0.096%

    No Known Activations