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

    Neuronpedia

    INDEX
    Explanations

    keyword detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    掄
    0.51
    Divid
    0.47
    नात्मक
    0.44
    Scanning
    0.41
    擎
    0.41
    वालियर
    0.41
    Writes
    0.41
    الم
    0.40
    فضل
    0.40
    лянчук
    0.40
    POSITIVE LOGITS
     sillä
    0.57
     pouvait
    0.48
     iar
    0.47
     Certification
    0.46
     hồng
    0.46
     certification
    0.44
     certify
    0.44
    ॉर
    0.43
     marriage
    0.43
     conjunction
    0.43
    Act Density 0.002%

    No Known Activations