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

    Neuronpedia

    INDEX
    Explanations

    current state or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.85
    ి
    1.54
     dve
    1.46
    ার
    1.44
    ER
    1.44
     அன்று
    1.42
    groupBox
    1.40
    ്
    1.40
    ед
    1.37
     "]";
    1.37
    POSITIVE LOGITS
    t
    2.38
    taker
    2.12
     yil
    1.88
    tım
    1.86
     affairs
    1.85
    tama
    1.78
    tib
    1.77
    tis
    1.76
    ^[
    1.74
    lly
    1.74
    Act Density 0.248%

    No Known Activations