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

    Neuronpedia

    INDEX
    Explanations

    direct questions and natural solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பண்டைய
    0.38
     étudiant
    0.38
    强烈
    0.38
    Giá
    0.37
     Dacă
    0.36
    འ
    0.36
    𝙶
    0.36
     électrique
    0.36
     étudiants
    0.36
     beş
    0.36
    POSITIVE LOGITS
     revision
    0.36
    [
    0.34
     version
    0.32
     conditioner
    0.31
     notebook
    0.30
    ity
    0.30
     recurrent
    0.30
    .
    0.30
     blog
    0.29
     bind
    0.29
    Act Density 0.228%

    No Known Activations