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

    Neuronpedia

    INDEX
    Explanations

    new breed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೋಜ
    0.38
     reunited
    0.38
     reun
    0.38
     MacL
    0.38
     Path
    0.38
    חד
    0.38
     reunion
    0.38
     Reun
    0.38
     заряд
    0.38
     congreg
    0.37
    POSITIVE LOGITS
     Reported
    0.46
     Jimmy
    0.45
    Jimmy
    0.41
     Report
    0.41
    Report
    0.41
     nelle
    0.40
     auront
    0.40
     റിപ്പോ
    0.39
     সম্পূর্ণরূপে
    0.39
     reported
    0.39
    Act Density 0.000%

    No Known Activations