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

    Neuronpedia

    INDEX
    Explanations

    modern/traditional descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concentrates
    0.44
     banknotes
    0.40
    資
    0.40
     exercise
    0.40
    Online
    0.40
    箕
    0.40
     Internet
    0.39
     appears
    0.39
     IPython
    0.38
    |
    0.38
    POSITIVE LOGITS
     bienvenidas
    0.60
     veulent
    0.57
     bienvenida
    0.52
     nuevas
    0.50
     voulait
    0.50
     quieren
    0.50
     نئے
    0.49
     kiddos
    0.49
     sassy
    0.49
     nieuwe
    0.48
    Act Density 0.006%

    No Known Activations