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

    Neuronpedia

    INDEX
    Explanations

    database cursor usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Beratung
    0.52
     Accountability
    0.52
     Consult
    0.50
    相談
    0.50
     Aprove
    0.50
     Uruguay
    0.49
    JAVA
    0.49
     sucre
    0.49
     Tugas
    0.49
    之外
    0.49
    POSITIVE LOGITS
    r
    0.61
    ız
    0.55
    into
    0.55
    ស្ន
    0.55
    lng
    0.54
    ről
    0.54
     počas
    0.53
     shēng
    0.53
    ِيم
    0.53
    larına
    0.52
    Act Density 0.013%

    No Known Activations