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

    Neuronpedia

    INDEX
    Explanations

    tuning in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     broadcast
    0.56
     films
    0.53
     broadcasting
    0.53
     movies
    0.51
    Movies
    0.50
    放送
    0.49
     film
    0.48
     фильмы
    0.48
     películas
    0.48
     documentaries
    0.47
    POSITIVE LOGITS
     tuning
    1.34
     Tuning
    1.30
     tuned
    1.14
    tuning
    1.10
     Tune
    1.09
     tune
    1.08
    Tune
    1.02
     tunable
    0.98
     Tun
    0.97
     tun
    0.96
    Act Density 0.011%

    No Known Activations