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

    Neuronpedia

    INDEX
    Explanations

    Industry 5.0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    警察
    0.47
    stars
    0.46
    Ві
    0.42
    Stars
    0.41
     pharmacists
    0.41
     for
    0.40
    headline
    0.40
     boissons
    0.39
     Policing
    0.39
     attorneys
    0.39
    POSITIVE LOGITS
    似的
    0.54
     пря
    0.46
     descrito
    0.42
     即
    0.41
     అలాగే
    0.41
    ບບ
    0.41
    (
    0.41
    INDOW
    0.41
     비슷한
    0.40
     mirip
    0.40
    Act Density 0.003%

    No Known Activations