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

    Neuronpedia

    INDEX
    Explanations

    chemical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoping
    0.69
     hope
    0.58
    希望
    0.58
     berharap
    0.52
     Hoping
    0.51
     Hoffnung
    0.48
    hope
    0.46
     esperanza
    0.46
     hoff
    0.46
     hopes
    0.45
    POSITIVE LOGITS
     Mn
    0.53
    蹶
    0.42
    Mn
    0.40
    astri
    0.40
    number
    0.37
    Mw
    0.37
     তফস
    0.37
     Firm
    0.37
    Número
    0.36
    补偿
    0.36
    Act Density 0.012%

    No Known Activations