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

    Neuronpedia

    INDEX
    Explanations

    remember that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lal
    0.45
    “,
    0.38
    alal
    0.38
     j
    0.37
    轨道
    0.37
    पणे
    0.36
     Lal
    0.35
     handbag
    0.35
     falo
    0.35
    행
    0.35
    POSITIVE LOGITS
     Chances
    0.53
     chances
    0.51
    Remember
    0.50
     remember
    0.49
     Remember
    0.48
     याद
    0.44
     Chancen
    0.43
    remember
    0.43
     remembers
    0.42
    arning
    0.39
    Act Density 0.000%

    No Known Activations