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

    Neuronpedia

    INDEX
    Explanations

    terms related to roles and user permissions in a system

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

    Code related to roles or actions

    np_acts-logits-general · gemini-2.0-flash

    code or data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')):
    -0.94
    ']?>
    -0.94
    }],
    -0.90
    ########.
    -0.86
    )))));
    -0.85
    )))),
    -0.82
    })));
    -0.81
    ))$.
    -0.81
    ")){
    -0.81
    ])));
    -0.81
    POSITIVE LOGITS
     forKey
    0.81
     else
    0.72
     than
    0.60
     about
    0.57
     vào
    0.57
    nale
    0.56
     davon
    0.56
     from
    0.54
     into
    0.54
    GetString
    0.54
    Act Density 1.015%

    No Known Activations