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

    Neuronpedia

    INDEX
    Explanations

    RTGs and space missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ีย
    0.56
    ры
    0.53
    $$\
    0.51
     THEY
    0.48
     کوشش
    0.47
     deporte
    0.47
    чі
    0.45
    ิ
    0.45
    чить
    0.44
    λαδή
    0.44
    POSITIVE LOGITS
    dom
    0.55
    dis
    0.54
    nd
    0.52
    tons
    0.51
    da
    0.50
    Charl
    0.49
     omissions
    0.49
    OMIC
    0.49
     İn
    0.49
     Programa
    0.49
    Act Density 0.000%

    No Known Activations