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

    Neuronpedia

    INDEX
    Explanations

    widely accepted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    many
    0.90
     many
    0.87
    veel
    0.82
     molte
    0.81
     många
    0.77
     Viele
    0.76
    Many
    0.74
     muchos
    0.72
     Many
    0.72
     Muchos
    0.71
    POSITIVE LOGITS
    held
    1.10
     held
    0.95
     Agreed
    0.88
    Held
    0.82
     Held
    0.80
     Accept
    0.78
     Accepted
    0.74
    DH
    0.73
     attended
    0.72
    σία
    0.72
    Act Density 0.107%

    No Known Activations