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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight similarity or difference

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

    comparing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.63
    StructEnd
    -0.60
     ſtate
    -0.58
    Diweddarwch
    -0.57
     NSError
    -0.56
     miſ
    -0.56
    StoryboardSegue
    -0.55
     surla
    -0.55
    ſelf
    -0.54
     ſche
    -0.53
    POSITIVE LOGITS
     adipis
    0.32
    0.30
    }}{(
    0.29
     aload
    0.29
    Datuak
    0.29
    smöglichkeiten
    0.28
    Hentet
    0.28
     Aid
    0.28
     Kräuter
    0.28
     Nanoparticles
    0.28
    Act Density 0.107%

    No Known Activations