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

    Neuronpedia

    INDEX
    Explanations

    provides benefit or advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recommendations
    0.42
    тоў
    0.41
     discoveries
    0.40
    汢
    0.39
     POV
    0.39
     dividends
    0.38
    فك
    0.38
    으니
    0.36
     ''.
    0.36
    鈷
    0.36
    POSITIVE LOGITS
    WE
    0.41
    ៉
    0.40
    INGTON
    0.40
     hadde
    0.39
     soruml
    0.39
    }^{+}=
    0.39
    ोरेंट
    0.39
     કર્મચારી
    0.39
    we
    0.38
     mengalami
    0.38
    Act Density 0.016%

    No Known Activations