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

    Neuronpedia

    INDEX
    Explanations

    rust public or attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chud
    0.44
    ధి
    0.40
     doh
    0.39
    !*\
    0.39
     consigned
    0.38
     cramping
    0.38
     possession
    0.37
    فوظ
    0.37
     rusting
    0.36
     heter
    0.36
    POSITIVE LOGITS
    pub
    0.70
    Pub
    0.60
     pub
    0.58
     Pub
    0.54
    #[
    0.47
     PUB
    0.45
     publie
    0.44
    PUB
    0.43
     #[
    0.43
     pubs
    0.43
    Act Density 0.003%

    No Known Activations