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

    Neuronpedia

    INDEX
    Explanations

    st. and saint names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    barung
    0.39
     भोग
    0.38
     മാലി
    0.37
     pandemic
    0.36
     soup
    0.36
     prolog
    0.36
     income
    0.36
    閑
    0.36
     pail
    0.36
     malignant
    0.36
    POSITIVE LOGITS
    몬
    0.44
     Theres
    0.44
    Ther
    0.43
     Tere
    0.41
     Theresa
    0.40
     Pio
    0.40
     ther
    0.39
     Pilar
    0.39
     Angela
    0.38
    Angela
    0.38
    Act Density 0.001%

    No Known Activations