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

    Neuronpedia

    INDEX
    Explanations

    reverse engineer API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QS
    0.44
    Qm
    0.40
    Timeout
    0.38
     =>
    0.38
    ").
    0.37
    TIMEOUT
    0.37
    ATE
    0.36
     بوت
    0.36
    EG
    0.36
    栓
    0.36
    POSITIVE LOGITS
    ၀၀
    0.43
     Ві
    0.41
    ূন
    0.40
     గో
    0.39
    goog
    0.39
     médic
    0.39
     unrest
    0.39
     uncut
    0.38
     Louisville
    0.38
     Unknown
    0.38
    Act Density 0.000%

    No Known Activations