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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and details in an obituary

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

    completing phrases after pronouns or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.41
     PicClick
    -0.36
     samar
    -0.34
     ninguno
    -0.34
     bloke
    -0.34
     bag
    -0.33
     strap
    -0.32
     check
    -0.32
    ]]:
    -0.32
     cuesta
    -0.31
    POSITIVE LOGITS
    SequentialGroup
    0.63
    ValueStyle
    0.62
    Życiorys
    0.61
    RegressionTest
    0.60
    UnusedPrivate
    0.59
     utafitiHapana
    0.58
    :✨
    0.56
    PMailer
    0.55
    +#+
    0.55
    AnimationsModule
    0.55
    Act Density 0.005%

    No Known Activations