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

    Neuronpedia

    INDEX
    Explanations

    mirror reflects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Buster
    0.61
     Flag
    0.60
    FU
    0.59
    ials
    0.59
    ads
    0.58
     Lind
    0.58
     Guant
    0.58
    et
    0.58
    h
    0.58
     Davos
    0.57
    POSITIVE LOGITS
    悩
    0.58
    𝐠
    0.57
     населения
    0.54
     buhay
    0.54
     recharging
    0.54
    ين
    0.53
     contesto
    0.52
    出错
    0.52
    及
    0.52
    ри
    0.52
    Act Density 0.001%

    No Known Activations