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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and documentation

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

    Accusations or explanations for one's actions

    np_acts-logits-general · gemini-2.0-flash

    his own statements and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ourselves
    -0.83
     deres
    -0.74
     our
    -0.71
     deras
    -0.63
    彼らは
    -0.62
     we
    -0.62
    กัน
    -0.61
     yourselves
    -0.60
     loro
    -0.59
    our
    -0.57
    POSITIVE LOGITS
     himself
    1.65
    himself
    1.36
     his
    1.19
     Himself
    1.07
    his
    0.93
     himſelf
    0.89
     seinem
    0.89
    حياته
    0.86
     consultato
    0.85
     seiner
    0.84
    Act Density 1.035%

    No Known Activations