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

    Neuronpedia

    INDEX
    Explanations

    RED Pyro, compose, week, R

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这一切
    0.42
    械
    0.38
    crystalline
    0.38
     сексуа
    0.37
     éd
    0.37
     vợ
    0.37
    nucleon
    0.36
     Solana
    0.36
     fiancée
    0.36
     روبل
    0.36
    POSITIVE LOGITS
     Zaman
    0.41
    тивными
    0.40
    il
    0.40
    hingga
    0.40
    toupper
    0.40
    Improved
    0.39
    tainable
    0.38
    /*.
    0.37
    logo
    0.37
    Mask
    0.37
    Act Density 0.000%

    No Known Activations