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

    Neuronpedia

    INDEX
    Explanations

    unicode escape sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viene
    0.43
    iii
    0.41
     kat
    0.38
    SMP
    0.38
     SMP
    0.37
     Deploy
    0.37
    రె
    0.37
     Yong
    0.36
     GRE
    0.36
     liz
    0.36
    POSITIVE LOGITS
    ={()=>
    0.40
     delegations
    0.39
    INavigation
    0.39
    மிருந்து
    0.38
    hygine
    0.38
    탤
    0.38
    CUSSION
    0.37
    េទ
    0.37
    ว์
    0.37
     lacs
    0.37
    Act Density 0.002%

    No Known Activations