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

    Neuronpedia

    INDEX
    Explanations

    expands grandeur generosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    才
    0.42
     dilig
    0.38
    ances
    0.37
    joining
    0.36
    flying
    0.35
    系の
    0.35
    しか
    0.35
    ığı
    0.35
     কাক
    0.35
    joins
    0.35
    POSITIVE LOGITS
     generous
    0.77
     generosity
    0.69
     magn
    0.66
     generously
    0.58
     grandeur
    0.57
     Magn
    0.54
    magn
    0.54
    Magn
    0.50
     expans
    0.50
     Gener
    0.49
    Act Density 0.000%

    No Known Activations