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

    Neuronpedia

    INDEX
    Explanations

    programming tools and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.54
    role
    0.47
    at
    0.47
    sobre
    0.47
    s
    0.45
    istance
    0.45
    width
    0.43
    inescent
    0.42
    oglobulin
    0.42
    Pedido
    0.42
    POSITIVE LOGITS
     LDAP
    0.53
    ᖕ
    0.52
     Sinatra
    0.51
    ἶ
    0.49
    硣
    0.49
    ᓵ
    0.49
     BUT
    0.48
    ᕈ
    0.47
    겉
    0.45
    醝
    0.45
    Act Density 0.003%

    No Known Activations