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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শ্রুতি
    0.38
    쉰
    0.37
    Adj
    0.37
    adj
    0.37
    Electronic
    0.37
    सेट
    0.37
     adj
    0.36
    箬
    0.36
    gend
    0.36
    ന്റി
    0.36
    POSITIVE LOGITS
     bridging
    0.44
     mysteries
    0.42
    牟
    0.39
    嬤
    0.39
    )++;
    0.38
    側の
    0.38
     tumorigen
    0.38
    튀
    0.38
    ύ
    0.37
    Dame
    0.37
    Act Density 0.002%

    No Known Activations