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

    Neuronpedia

    INDEX
    Explanations

    continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afterwards
    1.06
     afterward
    1.01
     পরে
    0.99
     Afterwards
    0.94
     नंतर
    0.88
    последствии
    0.85
     बाद
    0.84
     pozdě
    0.83
     Afterward
    0.82
     afterthought
    0.81
    POSITIVE LOGITS
     continue
    4.52
    continue
    4.37
     continues
    4.30
     continued
    4.26
     continuing
    4.07
     Continue
    3.99
    continues
    3.83
    continued
    3.78
    Continue
    3.78
     continuar
    3.55
    Act Density 0.250%

    No Known Activations