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

    Neuronpedia

    INDEX
    Explanations

    concerned for, want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    0.84
     colorful
    0.78
    م
    0.77
     heiß
    0.68
    дова
    0.65
     اصلا
    0.65
     diharapkan
    0.65
     imprim
    0.64
     höch
    0.64
     Unavailable
    0.64
    POSITIVE LOGITS
    Commande
    0.76
    ⤦
    0.75
    \\.
    0.72
    Cadastro
    0.71
    imizin
    0.70
    ⟢
    0.69
    {\
    0.68
    endment
    0.68
    atán
    0.68
    Ingrese
    0.67
    Act Density 0.793%

    No Known Activations