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

    Neuronpedia

    INDEX
    Explanations

    register / registry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.55
    ρ
    0.47
     like
    0.46
    prepareStatement
    0.45
    :]
    0.45
     п
    0.44
    wrote
    0.43
     θ
    0.43
    tahun
    0.43
    П
    0.43
    POSITIVE LOGITS
    छोटी
    0.46
     Microscopy
    0.44
    amah
    0.44
     riguardo
    0.44
     marches
    0.43
     encargado
    0.42
    िसो
    0.42
    cloudinary
    0.42
    لوث
    0.42
     मोर्चा
    0.42
    Act Density 0.002%

    No Known Activations