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

    Neuronpedia

    INDEX
    Explanations

    then followed by pronoun or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    0.62
    us
    0.60
    ax
    0.60
    0
    0.57
    ak
    0.56
    ind
    0.56
    ist
    0.55
     rồi
    0.55
     Затем
    0.54
    ts
    0.54
    POSITIVE LOGITS
     neither
    0.56
     it
    0.52
     indeed
    0.52
     there
    0.50
     thisobject
    0.46
     encontramos
    0.46
     encuentre
    0.46
    こそ
    0.46
    まさに
    0.46
    miyor
    0.46
    Act Density 0.010%

    No Known Activations