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

    Neuronpedia

    INDEX
    Explanations

    discourse about societal issues and political dynamics

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

    Follows a comma or conjunction

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HostException
    -0.85
    }\]
    -0.77
     Италијани
    -0.73
    titleMargin
    -0.72
    fromnode
    -0.67
     useAppContext
    -0.64
    )*/
    -0.62
     Krakowie
    -0.61
    ]));
    -0.61
    GrantedAuthority
    -0.61
    POSITIVE LOGITS
     everything
    0.51
    就不会
    0.50
     Problem
    0.48
     will
    0.48
    everything
    0.46
    Problem
    0.46
     problem
    0.45
    就能
    0.45
    SuppressLint
    0.45
    portlet
    0.44
    Act Density 0.345%

    No Known Activations