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

    Neuronpedia

    INDEX
    Explanations

    social events and games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fl
    0.49
    et
    0.48
    ediat
    0.48
    five
    0.47
    qus
    0.47
    Qs
    0.47
    set
    0.47
    H
    0.47
    Fs
    0.46
    gwood
    0.46
    POSITIVE LOGITS
     pequeno
    0.53
    一個
    0.47
    시기
    0.44
     fabriqu
    0.44
     최고의
    0.44
     família
    0.43
     siendo
    0.43
     AdapterView
    0.43
    тери
    0.43
    着
    0.43
    Act Density 0.001%

    No Known Activations