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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and testimonies

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

    past events or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ţional
    -0.42
    principalTable
    -0.38
     iconLine
    -0.37
    rillation
    -0.36
    Сылтамалар
    -0.35
    Carreira
    -0.35
     Simple
    -0.35
    Diweddarwch
    -0.35
    *}$
    -0.34
     ***!
    -0.34
    POSITIVE LOGITS
     himself
    0.55
    himself
    0.50
     himſelf
    0.49
    pecabe
    0.49
    +#+
    0.47
     enfans
    0.47
     zijne
    0.45
     ſeine
    0.43
    optarg
    0.43
     noiva
    0.41
    Act Density 0.445%

    No Known Activations