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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recent trends or changes

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

    recent or lately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elesaikan
    -0.35
     fertig
    -0.35
     still
    -0.35
     Oppen
    -0.34
    RTCF
    -0.34
     Reiche
    -0.33
     perfectly
    -0.32
     unut
    -0.32
     totally
    -0.32
     idealism
    -0.31
    POSITIVE LOGITS
    Recent
    0.91
     Lately
    0.86
    recent
    0.86
     recent
    0.82
     lately
    0.82
     Recent
    0.81
     recente
    0.80
     recenti
    0.75
     recentes
    0.75
     RECENT
    0.74
    Act Density 0.207%

    No Known Activations