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

    Neuronpedia

    INDEX
    Explanations

    optimal results and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psychiatrists
    0.44
     Quadratic
    0.43
     confiscated
    0.42
     UserRepository
    0.42
     throne
    0.40
     booming
    0.39
     ибо
    0.39
     {
    0.39
     కూడా
    0.39
     downright
    0.38
    POSITIVE LOGITS
     sản
    0.45
     actriz
    0.44
     chantier
    0.44
    釀
    0.43
     atriz
    0.43
     മറ്റൊരു
    0.43
     bisnis
    0.43
    バランス
    0.43
     melhores
    0.42
     zmian
    0.42
    Act Density 0.001%

    No Known Activations