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

    Neuronpedia

    INDEX
    Explanations

    structured steps or instructions

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

    introducing lists or steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.75
    IntoConstraints
    -0.67
    Jeografia
    -0.59
     myſelf
    -0.58
    Personensuche
    -0.58
     whoſe
    -0.57
     zijne
    -0.56
     Forumite
    -0.53
    neſs
    -0.53
     ſhe
    -0.53
    POSITIVE LOGITS
     EClass
    0.44
     ask
    0.36
     din
    0.34
    дравству
    0.34
    Organisateur
    0.33
     Din
    0.32
    째
    0.32
     opt
    0.31
    ※
    0.31
     dintre
    0.31
    Act Density 0.222%

    No Known Activations