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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of politics

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

    politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeiti
    -0.47
    unhofer
    -0.44
     outstanding
    -0.39
    Rptr
    -0.39
     Historical
    -0.39
    ocardial
    -0.37
    \)
    -0.37
    Esperamos
    -0.36
     Ślą
    -0.36
    elded
    -0.36
    POSITIVE LOGITS
     politics
    2.03
     Politics
    1.86
    politics
    1.83
    Politics
    1.73
     POLITICS
    1.72
     Politik
    1.13
    politik
    1.09
    POLIT
    1.03
    Politik
    0.99
     politik
    0.98
    Act Density 0.004%

    No Known Activations