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

    Neuronpedia

    INDEX
    Explanations

    day update, allows access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    де
    1.09
    น
    1.04
    П
    0.99
    Dist
    0.93
    Ens
    0.92
    En
    0.91
    Mem
    0.89
    PING
    0.89
    P
    0.88
    \]
    0.87
    POSITIVE LOGITS
     казни
    0.94
     việc
    0.89
    ights
    0.88
    halb
    0.87
    imation
    0.86
    enix
    0.81
     giãn
    0.78
    falen
    0.77
    sburg
    0.77
     zeker
    0.76
    Act Density 0.000%

    No Known Activations