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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.52
    warn
    0.49
     s
    0.48
    t
    0.46
     Agencies
    0.45
     Attitudes
    0.45
    ag
    0.45
     entities
    0.45
    står
    0.44
     agencies
    0.43
    POSITIVE LOGITS
     встанов
    0.60
     출
    0.53
    SDAY
    0.52
     ഔ
    0.52
     이전
    0.52
    ⤦
    0.50
    ভক্ত
    0.49
     způ
    0.48
    ചെയ്യ
    0.48
    ออกจาก
    0.48
    Act Density 0.001%

    No Known Activations