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

    Neuronpedia

    INDEX
    Explanations

    also tend to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     think
    0.66
    think
    0.55
    Think
    0.53
    িদ্ধ
    0.53
     spring
    0.50
     twin
    0.49
     search
    0.49
    z
    0.49
     thinks
    0.48
    er
    0.47
    POSITIVE LOGITS
     Oliveira
    0.53
    <unused671>
    0.49
    <unused480>
    0.49
     cải
    0.47
     logotipo
    0.47
     अशा
    0.47
     oligarch
    0.47
    薩
    0.47
    ங்களிலிருந்து
    0.46
     adulto
    0.46
    Act Density 0.000%

    No Known Activations