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

    Neuronpedia

    INDEX
    Explanations

    long descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tier
    0.66
     Robust
    0.54
     Grandma
    0.53
    )="
    0.53
     tier
    0.53
    डॉ
    0.52
    氳
    0.52
     Schein
    0.50
     Governor
    0.50
     Mom
    0.50
    POSITIVE LOGITS
    lasting
    1.19
     длин
    1.16
     lasting
    1.14
     duração
    1.13
     duration
    1.10
    长的
    1.08
     duración
    1.07
     dài
    1.06
     ago
    1.05
    itudes
    1.05
    Act Density 0.195%

    No Known Activations