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

    Neuronpedia

    INDEX
    Explanations

    references to repair and fastening processes

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

    patching or filling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sahiptir
    -0.30
     değildir
    -0.30
     bēr
    -0.29
    bebasan
    -0.28
     Internasional
    -0.27
     Erziehung
    -0.27
     Regierung
    -0.26
     democracia
    -0.25
     libertad
    -0.24
     droits
    -0.23
    POSITIVE LOGITS
     repair
    0.90
    Repair
    0.88
    repair
    0.88
    oa̍t
    0.88
     repairs
    0.88
    GEBURTSDATUM
    0.86
     Repairs
    0.84
     Repair
    0.83
    <unused3>
    0.80
    <unused14>
    0.80
    Act Density 0.013%

    No Known Activations