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

    Neuronpedia

    INDEX
    Explanations

    even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פט
    0.46
    :“
    0.44
    ”।
    0.43
    :
    0.42
    貞
    0.41
    નમાં
    0.40
    ంపు
    0.40
    撲
    0.40
    ]:
    0.40
    '।
    0.40
    POSITIVE LOGITS
     JavaBeans
    0.47
     ory
    0.46
     malzeme
    0.45
     comer
    0.44
    javascripts
    0.44
    ardini
    0.43
     materiais
    0.43
     ceramics
    0.42
     textura
    0.42
     Kanban
    0.42
    Act Density 0.000%

    No Known Activations