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

    Neuronpedia

    INDEX
    Explanations

    elements related to the understanding and functioning of democracy

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

    Following "what's" or "what is"

    np_acts-logits-general · gemini-2.0-flash

    understanding how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.84
    ſelf
    -0.80
    ſelves
    -0.76
    ſehen
    -0.70
    linawan
    -0.70
     nakalista
    -0.69
    niſſe
    -0.68
    mbgg
    -0.68
    iſen
    -0.68
    ſicht
    -0.68
    POSITIVE LOGITS
     how
    0.41
    how
    0.35
     itself
    0.34
    是如何
    0.33
     themselves
    0.32
     Wirkung
    0.31
     sebenar
    0.31
    如何
    0.29
    How
    0.29
     cómo
    0.29
    Act Density 0.601%

    No Known Activations