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

    Neuronpedia

    INDEX
    Explanations

    frequency or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    G
    0.38
    recall
    0.37
    द्वारा
    0.37
    ًا
    0.37
     Speaks
    0.37
    WE
    0.36
     penjelasan
    0.36
     prilikom
    0.36
    ३
    0.36
     terdapat
    0.35
    POSITIVE LOGITS
     slowly
    0.50
     используя
    0.50
     עם
    0.49
     twice
    0.49
     WITH
    0.49
     immediately
    0.47
     asap
    0.47
     sparingly
    0.45
     πρώτη
    0.45
     sweetened
    0.44
    Act Density 0.009%

    No Known Activations