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

    Neuronpedia

    INDEX
    Explanations

    expect, need, choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     druga
    0.72
    essere
    0.69
     شكله
    0.67
     verdiği
    0.67
     yaptığı
    0.66
    etheless
    0.65
     permette
    0.65
    sockfd
    0.65
    ἀ
    0.64
    ﻧ
    0.64
    POSITIVE LOGITS
     here
    0.83
     of
    0.79
     choose
    0.77
     need
    0.74
     इन
    0.73
     find
    0.72
     expect
    0.72
     wählen
    0.72
     encounter
    0.72
     auswählen
    0.71
    Act Density 0.291%

    No Known Activations