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

    Neuronpedia

    INDEX
    Explanations

    come back, interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     come
    0.43
     goin
    0.42
     লেগে
    0.40
     komma
    0.39
     tutt
    0.38
    喧
    0.38
     going
    0.37
     pote
    0.37
     battaglia
    0.37
    thin
    0.37
    POSITIVE LOGITS
     Interest
    0.41
    兴趣
    0.40
    面对
    0.40
     INTEREST
    0.39
     Interests
    0.38
    瑚
    0.37
     Real
    0.37
     ausgest
    0.37
    geist
    0.36
     interest
    0.36
    Act Density 0.004%

    No Known Activations