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

    Neuronpedia

    INDEX
    Explanations

    references to reductions in costs or government initiatives

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

    movement down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.53
     nakalista
    -0.52
    cibly
    -0.49
    CppMethod
    -0.48
     endwhile
    -0.47
    optarg
    -0.46
    ="@+
    -0.46
    cerely
    -0.44
     hierv
    -0.44
    minipage
    -0.44
    POSITIVE LOGITS
     downfall
    0.59
     downed
    0.54
    يكب
    0.52
    verwijspagina
    0.52
     inflation
    0.49
     lowering
    0.47
     lowers
    0.47
     DOWN
    0.46
     down
    0.46
     caída
    0.44
    Act Density 0.009%

    No Known Activations