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

    Neuronpedia

    INDEX
    Explanations

    residing or located at addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आपने
    0.42
    Closeup
    0.39
    Episodes
    0.37
    脍
    0.36
     lacked
    0.36
     infamous
    0.36
     Preheat
    0.36
     Kuznet
    0.35
    跗
    0.35
     paprika
    0.35
    POSITIVE LOGITS
    represented
    0.88
     represented
    0.87
     representado
    0.84
     representada
    0.72
     hereinafter
    0.71
    hereinafter
    0.65
     représent
    0.57
     hereafter
    0.55
     vertreten
    0.54
    hereafter
    0.54
    Act Density 0.007%

    No Known Activations