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

    Neuronpedia

    INDEX
    Explanations

    commands or actions related to navigating or moving to a different context or place

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

    go or going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sánchez
    -0.72
     ainfi
    -0.68
    ientras
    -0.65
     isEnabled
    -0.64
    ßerdem
    -0.61
     fernández
    -0.61
     gynhyrchwyd
    -0.60
    了嗎
    -0.59
    bbene
    -0.59
     belangrij
    -0.58
    POSITIVE LOGITS
    去
    1.70
     去
    1.39
    就去
    1.00
    你去
    0.95
    再去
    0.93
    想去
    0.93
    要去
    0.90
    不去
    0.85
    我去
    0.81
    去的
    0.74
    Act Density 0.001%

    No Known Activations