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

    Neuronpedia

    INDEX
    Explanations

    cons and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unsightly
    0.53
     부담
    0.52
    proble
    0.52
     बाधा
    0.50
     महंगा
    0.48
    麻烦
    0.47
    性和
    0.47
    ವಲ್ಲ
    0.47
     infringing
    0.47
     പ്രശ്
    0.46
    POSITIVE LOGITS
     Steck
    0.45
     Zer
    0.44
     forwards
    0.43
     En
    0.42
     Etienne
    0.42
     método
    0.42
     Bruce
    0.42
     Zero
    0.40
     Typical
    0.40
     Dorothy
    0.40
    Act Density 0.099%

    No Known Activations