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

    Neuronpedia

    INDEX
    Explanations

    village, Tiber, Post, Gable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    auh
    0.38
    豢
    0.38
    provide
    0.38
    “
    0.38
     encourages
    0.37
     precludes
    0.37
     elegantly
    0.37
    offers
    0.36
    appreci
    0.36
    offer
    0.36
    POSITIVE LOGITS
     avem
    0.39
     parole
    0.38
     miserable
    0.38
     нашем
    0.38
     Assigned
    0.38
    ได
    0.38
     workable
    0.37
     Temos
    0.37
     messed
    0.37
     scrat
    0.37
    Act Density 0.015%

    No Known Activations