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

    Neuronpedia

    INDEX
    Explanations

    words related to legal standards and responsibilities

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

    no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一代
    -0.38
    客
    -0.36
     Tada
    -0.35
     multiple
    -0.33
    Morfo
    -0.32
    ______
    -0.31
     meyd
    -0.31
     Huff
    -0.31
     Wild
    -0.31
     autres
    -0.31
    POSITIVE LOGITS
     nessuno
    0.66
     jamás
    0.60
    tvguidetime
    0.58
     Majefty
    0.56
    Aucun
    0.54
     Efq
    0.52
     None
    0.52
     nahilalakip
    0.52
     podjela
    0.52
    Nowhere
    0.51
    Act Density 0.070%

    No Known Activations