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

    Neuronpedia

    INDEX
    Explanations

    code context, programming, data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    洒
    0.22
    နိုင်
    0.20
     রস
    0.20
    ческих
    0.20
    jecha
    0.19
    แบบ
    0.19
    粪
    0.19
    뿡
    0.19
     जिम्मेदार
    0.19
     прави
    0.18
    POSITIVE LOGITS
     it
    0.28
    this
    0.25
     this
    0.24
     their
    0.22
     contemplating
    0.21
     its
    0.21
     !(
    0.20
     current
    0.20
     cujo
    0.20
    தியின்
    0.19
    Act Density 0.441%

    No Known Activations