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

    Neuronpedia

    INDEX
    Explanations

    final answer boxed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Index
    0.83
     forKey
    0.83
    Applied
    0.82
    Build
    0.82
     Tetapi
    0.82
     beforeEach
    0.81
     metallurgy
    0.81
    )/(
    0.80
     appelle
    0.79
     빨리
    0.79
    POSITIVE LOGITS
    gação
    0.68
     rég
    0.60
     nic
    0.57
    एनजी
    0.57
     relief
    0.56
    捨
    0.56
    ряд
    0.55
     day
    0.55
    ঃখ
    0.55
     max
    0.54
    Act Density 0.021%

    No Known Activations