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

    Neuronpedia

    INDEX
    Explanations

    help USA service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Genome
    0.41
    Paxos
    0.40
    Genome
    0.39
     अभिगमन
    0.38
    FUEL
    0.38
     जनजाति
    0.38
     FUEL
    0.37
     Comune
    0.37
     pasting
    0.37
     시험
    0.37
    POSITIVE LOGITS
    USA
    0.68
     USA
    0.68
    usa
    0.66
     usa
    0.60
     Usa
    0.54
     abuso
    0.50
     abuse
    0.47
     ceb
    0.42
     misuse
    0.41
     bek
    0.40
    Act Density 0.005%

    No Known Activations