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

    Neuronpedia

    INDEX
    Explanations

    Brake hose and considered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oops
    0.46
    م
    0.46
     Tales
    0.46
    قابل
    0.45
     Naam
    0.44
     hör
    0.44
     Construction
    0.43
     Masters
    0.42
     Semin
    0.42
     Design
    0.42
    POSITIVE LOGITS
    зацию
    0.48
    又は
    0.46
     मुलांना
    0.46
    柤
    0.45
     ಇದರ
    0.45
    もしくは
    0.44
     ㅅ
    0.43
    력이
    0.43
     혹은
    0.43
    awsze
    0.43
    Act Density 0.001%

    No Known Activations