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

    Neuronpedia

    INDEX
    Explanations

    your body or personal space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wollten
    1.04
     waren
    1.03
     erano
    1.01
     تھیں
    1.01
    Were
    0.96
     Were
    0.96
     olid
    0.94
     говорили
    0.93
     использовали
    0.93
     wollte
    0.92
    POSITIVE LOGITS
     enjoys
    1.40
     thrives
    1.37
     operates
    1.08
     undergoes
    1.07
     receives
    1.03
     interacts
    1.02
     occupies
    1.02
     enjoy
    0.99
     manages
    0.98
     scarcely
    0.96
    Act Density 0.000%

    No Known Activations