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

    Neuronpedia

    INDEX
    Explanations

    current directory or invention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Published
    0.51
    Existing
    0.50
     existing
    0.48
     Published
    0.47
     Existing
    0.47
     existentes
    0.44
    published
    0.43
     published
    0.41
     соответству
    0.41
     существу
    0.41
    POSITIVE LOGITS
     invention
    0.84
    invention
    0.68
     invent
    0.56
     INVENTION
    0.53
     Invention
    0.51
     изобре
    0.51
    发明
    0.49
     inventions
    0.47
     inventing
    0.46
    invent
    0.46
    Act Density 0.006%

    No Known Activations