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

    Neuronpedia

    INDEX
    Explanations

    specific context or focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rection
    0.51
    tk
    0.49
    ts
    0.49
    tsy
    0.47
    ve
    0.44
    basics
    0.43
    tic
    0.43
    things
    0.43
    stuff
    0.43
    kt
    0.43
    POSITIVE LOGITS
     প্রেক্ষ
    0.50
    MISSIONS
    0.42
     specifico
    0.42
     preciso
    0.40
    十年
    0.39
    alé
    0.38
    engkap
    0.38
    打破
    0.38
     střed
    0.38
     contexte
    0.37
    Act Density 0.002%

    No Known Activations