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

    Neuronpedia

    INDEX
    Explanations

    Goo goo ga ga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.57
    endido
    0.56
    ive
    0.53
    كلم
    0.52
    𝒕
    0.49
    тых
    0.49
     பாலை
    0.49
    শোধ
    0.48
    صل
    0.47
    في
    0.46
    POSITIVE LOGITS
     Hat
    0.51
     Zheng
    0.48
    Hat
    0.47
     HAT
    0.47
    Su
    0.46
    k
    0.45
     Tur
    0.45
    Repository
    0.45
    Roaming
    0.45
     >>
    0.44
    Act Density 0.000%

    No Known Activations