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

    Neuronpedia

    INDEX
    Explanations

    installation commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Posterior
    0.89
     Excav
    0.85
     Emma
    0.81
     menyenangkan
    0.81
     Feelings
    0.81
     Act
    0.80
     Prolong
    0.79
     Doppel
    0.79
     Expedition
    0.78
     unmistak
    0.77
    POSITIVE LOGITS
     також
    1.04
     inoltre
    1.02
    otherapie
    1.01
     также
    0.99
     ayrıca
    0.99
    urrence
    0.99
    بيوتر
    0.98
    カイブ
    0.92
     verifica
    0.92
    unittest
    0.92
    Act Density 0.067%

    No Known Activations