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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superst
    -0.07
     Lean
    -0.06
    larındaki
    -0.06
    ner
    -0.06
    jišť
    -0.06
    ham
    -0.06
    ої
    -0.06
     rằng
    -0.06
    ken
    -0.06
    .cal
    -0.06
    POSITIVE LOGITS
     Bett
    0.06
     Bras
    0.06
    irmed
    0.06
     акту
    0.06
     zad
    0.06
     ут
    0.06
     Cory
    0.06
     यद
    0.06
    Crud
    0.06
    젝트
    0.06
    Act Density 0.048%

    No Known Activations