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

    Neuronpedia

    INDEX
    Explanations

    exceptions, pardons, excuses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    強制
    0.73
    ICKS
    0.69
    icks
    0.68
     locking
    0.66
     الممل
    0.65
     замы
    0.64
    噛
    0.62
    ᱠ
    0.61
    ricting
    0.60
    ricts
    0.60
    POSITIVE LOGITS
     pardon
    2.00
     exemption
    1.95
     exemptions
    1.84
     forgiveness
    1.78
     pard
    1.74
     forgiven
    1.64
     amnesty
    1.64
     exempt
    1.62
     reprieve
    1.57
     exempted
    1.57
    Act Density 0.423%

    No Known Activations